<?xml version="1.0"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
	<id>https://music-ir.org/mirex/w/api.php?action=feedcontributions&amp;feedformat=atom&amp;user=Ming-Chi+Yen</id>
	<title>MIREX Wiki - User contributions [en]</title>
	<link rel="self" type="application/atom+xml" href="https://music-ir.org/mirex/w/api.php?action=feedcontributions&amp;feedformat=atom&amp;user=Ming-Chi+Yen"/>
	<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/wiki/Special:Contributions/Ming-Chi_Yen"/>
	<updated>2026-04-13T20:19:13Z</updated>
	<subtitle>User contributions</subtitle>
	<generator>MediaWiki 1.31.1</generator>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12363</id>
		<title>2017:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12363"/>
		<updated>2017-10-25T15:42:49Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* General Legend */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; | Sub code&lt;br /&gt;
    ! width=&amp;quot;200&amp;quot; | Submission name&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; style=&amp;quot;text-align: center;&amp;quot; | Abstract&lt;br /&gt;
    ! width=&amp;quot;540&amp;quot; | Contributors&lt;br /&gt;
    |-&lt;br /&gt;
&lt;br /&gt;
    ! HW1&lt;br /&gt;
    | style=&amp;quot;text-align: center;&amp;quot; | HW1 || -- || Hao Wu&lt;br /&gt;
    |-&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 001 !! 981.139 !! 990.869&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 002 !! 22.635 !!	18.241&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 024 !! 13.844 !!  25.790&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 036 !! 87.284  !!  106.569&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 043 !! 45.356 !! 68.930&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 069 !! 117.310  !! 132.401&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 073 !! 100.163 !! 107.107&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 195.390 !!  207.130&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 004 !! 85.503 !! 93.824&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 005 !! 788.662 !! 757.016&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 009 !! 130.044 !! 133.727&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 031 !! 125.346 !! 138.079&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 046 !! 390.230 !! 403.667&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 047 !! 408.388 !! 419.384&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 048 !! 36.138  !! 33.607&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 065 !! 301.346 !! 288.696&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 066 !! 75.162  !! 77.773&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 067 !! 231.737 !! 231.400&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 070 !! 87.586  !! 109.931&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 076 !! 50.321  !! 62.625&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 077 !! 490.394 !! 522.190&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 246.220 !! 251.686&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
===Summary===&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 320px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Sub Code&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg sBD&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg eBD&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! HW1 !! 220.805 !! 229.408&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12362</id>
		<title>2017:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12362"/>
		<updated>2017-10-25T15:40:12Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* General Legend */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
== General Legend ==&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; | Sub code&lt;br /&gt;
    ! width=&amp;quot;200&amp;quot; | Submission name&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; style=&amp;quot;text-align: center;&amp;quot; | Abstract&lt;br /&gt;
    ! width=&amp;quot;540&amp;quot; | Contributors&lt;br /&gt;
    |-&lt;br /&gt;
&lt;br /&gt;
    ! HW1&lt;br /&gt;
    | HW1  ||  style=&amp;quot;text-align: center;&amp;quot; ||   |  |&lt;br /&gt;
    |-&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 001 !! 981.139 !! 990.869&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 002 !! 22.635 !!	18.241&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 024 !! 13.844 !!  25.790&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 036 !! 87.284  !!  106.569&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 043 !! 45.356 !! 68.930&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 069 !! 117.310  !! 132.401&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 073 !! 100.163 !! 107.107&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 195.390 !!  207.130&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 004 !! 85.503 !! 93.824&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 005 !! 788.662 !! 757.016&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 009 !! 130.044 !! 133.727&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 031 !! 125.346 !! 138.079&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 046 !! 390.230 !! 403.667&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 047 !! 408.388 !! 419.384&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 048 !! 36.138  !! 33.607&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 065 !! 301.346 !! 288.696&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 066 !! 75.162  !! 77.773&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 067 !! 231.737 !! 231.400&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 070 !! 87.586  !! 109.931&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 076 !! 50.321  !! 62.625&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 077 !! 490.394 !! 522.190&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 246.220 !! 251.686&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
===Summary===&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 320px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Sub Code&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg sBD&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg eBD&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! HW1 !! 220.805 !! 229.408&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12361</id>
		<title>2017:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12361"/>
		<updated>2017-10-25T15:39:53Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* General Legend */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
== General Legend ==&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; | Sub code&lt;br /&gt;
    ! width=&amp;quot;200&amp;quot; | Submission name&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; style=&amp;quot;text-align: center;&amp;quot; | Abstract&lt;br /&gt;
    ! width=&amp;quot;540&amp;quot; | Contributors&lt;br /&gt;
    |-&lt;br /&gt;
&lt;br /&gt;
    ! HW1&lt;br /&gt;
    | HW1  ||  style=&amp;quot;text-align: center;&amp;quot; ||   | &lt;br /&gt;
    |-&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 001 !! 981.139 !! 990.869&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 002 !! 22.635 !!	18.241&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 024 !! 13.844 !!  25.790&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 036 !! 87.284  !!  106.569&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 043 !! 45.356 !! 68.930&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 069 !! 117.310  !! 132.401&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 073 !! 100.163 !! 107.107&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 195.390 !!  207.130&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 004 !! 85.503 !! 93.824&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 005 !! 788.662 !! 757.016&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 009 !! 130.044 !! 133.727&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 031 !! 125.346 !! 138.079&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 046 !! 390.230 !! 403.667&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 047 !! 408.388 !! 419.384&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 048 !! 36.138  !! 33.607&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 065 !! 301.346 !! 288.696&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 066 !! 75.162  !! 77.773&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 067 !! 231.737 !! 231.400&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 070 !! 87.586  !! 109.931&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 076 !! 50.321  !! 62.625&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 077 !! 490.394 !! 522.190&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 246.220 !! 251.686&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
===Summary===&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 320px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Sub Code&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg sBD&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg eBD&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! HW1 !! 220.805 !! 229.408&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12360</id>
		<title>2017:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12360"/>
		<updated>2017-10-25T15:39:18Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* General Legend */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
== General Legend ==&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; | Sub code&lt;br /&gt;
    ! width=&amp;quot;200&amp;quot; | Submission name&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; style=&amp;quot;text-align: center;&amp;quot; | Abstract&lt;br /&gt;
    ! width=&amp;quot;540&amp;quot; | Contributors&lt;br /&gt;
    |-&lt;br /&gt;
&lt;br /&gt;
    ! HW1&lt;br /&gt;
    | HW1  ||  style=&amp;quot;text-align: center;&amp;quot; ||  !!  Hao Wu | &lt;br /&gt;
    |-&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 001 !! 981.139 !! 990.869&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 002 !! 22.635 !!	18.241&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 024 !! 13.844 !!  25.790&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 036 !! 87.284  !!  106.569&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 043 !! 45.356 !! 68.930&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 069 !! 117.310  !! 132.401&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 073 !! 100.163 !! 107.107&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 195.390 !!  207.130&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 004 !! 85.503 !! 93.824&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 005 !! 788.662 !! 757.016&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 009 !! 130.044 !! 133.727&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 031 !! 125.346 !! 138.079&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 046 !! 390.230 !! 403.667&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 047 !! 408.388 !! 419.384&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 048 !! 36.138  !! 33.607&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 065 !! 301.346 !! 288.696&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 066 !! 75.162  !! 77.773&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 067 !! 231.737 !! 231.400&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 070 !! 87.586  !! 109.931&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 076 !! 50.321  !! 62.625&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 077 !! 490.394 !! 522.190&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 246.220 !! 251.686&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
===Summary===&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 320px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Sub Code&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg sBD&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg eBD&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! HW1 !! 220.805 !! 229.408&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12359</id>
		<title>2017:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12359"/>
		<updated>2017-10-25T15:38:38Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* General Legend */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
== General Legend ==&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; | Sub code&lt;br /&gt;
    ! width=&amp;quot;200&amp;quot; | Submission name&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; style=&amp;quot;text-align: center;&amp;quot; | Abstract&lt;br /&gt;
    ! width=&amp;quot;540&amp;quot; | Contributors&lt;br /&gt;
    |-&lt;br /&gt;
&lt;br /&gt;
    ! HW1&lt;br /&gt;
    | HW1  ||  style=&amp;quot;text-align: center;&amp;quot; ||  |  Hao Wu | &lt;br /&gt;
    |-&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 001 !! 981.139 !! 990.869&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 002 !! 22.635 !!	18.241&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 024 !! 13.844 !!  25.790&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 036 !! 87.284  !!  106.569&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 043 !! 45.356 !! 68.930&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 069 !! 117.310  !! 132.401&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 073 !! 100.163 !! 107.107&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 195.390 !!  207.130&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 004 !! 85.503 !! 93.824&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 005 !! 788.662 !! 757.016&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 009 !! 130.044 !! 133.727&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 031 !! 125.346 !! 138.079&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 046 !! 390.230 !! 403.667&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 047 !! 408.388 !! 419.384&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 048 !! 36.138  !! 33.607&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 065 !! 301.346 !! 288.696&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 066 !! 75.162  !! 77.773&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 067 !! 231.737 !! 231.400&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 070 !! 87.586  !! 109.931&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 076 !! 50.321  !! 62.625&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 077 !! 490.394 !! 522.190&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 246.220 !! 251.686&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
===Summary===&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 320px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Sub Code&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg sBD&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg eBD&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! HW1 !! 220.805 !! 229.408&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12358</id>
		<title>2017:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12358"/>
		<updated>2017-10-25T15:38:09Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* General Legend */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
== General Legend ==&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; | Sub code&lt;br /&gt;
    ! width=&amp;quot;200&amp;quot; | Submission name&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; style=&amp;quot;text-align: center;&amp;quot; | Abstract&lt;br /&gt;
    ! width=&amp;quot;540&amp;quot; | Contributors&lt;br /&gt;
    |-&lt;br /&gt;
&lt;br /&gt;
    ! HW1&lt;br /&gt;
    | HW1  ||  style=&amp;quot;text-align: center;&amp;quot; ||  || Hao Wu | &lt;br /&gt;
    |-&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 001 !! 981.139 !! 990.869&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 002 !! 22.635 !!	18.241&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 024 !! 13.844 !!  25.790&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 036 !! 87.284  !!  106.569&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 043 !! 45.356 !! 68.930&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 069 !! 117.310  !! 132.401&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 073 !! 100.163 !! 107.107&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 195.390 !!  207.130&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 004 !! 85.503 !! 93.824&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 005 !! 788.662 !! 757.016&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 009 !! 130.044 !! 133.727&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 031 !! 125.346 !! 138.079&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 046 !! 390.230 !! 403.667&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 047 !! 408.388 !! 419.384&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 048 !! 36.138  !! 33.607&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 065 !! 301.346 !! 288.696&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 066 !! 75.162  !! 77.773&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 067 !! 231.737 !! 231.400&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 070 !! 87.586  !! 109.931&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 076 !! 50.321  !! 62.625&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 077 !! 490.394 !! 522.190&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 246.220 !! 251.686&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
===Summary===&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 320px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Sub Code&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg sBD&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg eBD&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! HW1 !! 220.805 !! 229.408&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12357</id>
		<title>2017:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12357"/>
		<updated>2017-10-25T15:37:53Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* General Legend */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
== General Legend ==&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; | Sub code&lt;br /&gt;
    ! width=&amp;quot;200&amp;quot; | Submission name&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; style=&amp;quot;text-align: center;&amp;quot; | Abstract&lt;br /&gt;
    ! width=&amp;quot;540&amp;quot; | Contributors&lt;br /&gt;
    |-&lt;br /&gt;
&lt;br /&gt;
    ! HW1&lt;br /&gt;
    | HW1  ||  style=&amp;quot;text-align: center;&amp;quot; ||  Hao Wu | &lt;br /&gt;
    |-&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 001 !! 981.139 !! 990.869&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 002 !! 22.635 !!	18.241&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 024 !! 13.844 !!  25.790&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 036 !! 87.284  !!  106.569&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 043 !! 45.356 !! 68.930&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 069 !! 117.310  !! 132.401&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 073 !! 100.163 !! 107.107&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 195.390 !!  207.130&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 004 !! 85.503 !! 93.824&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 005 !! 788.662 !! 757.016&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 009 !! 130.044 !! 133.727&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 031 !! 125.346 !! 138.079&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 046 !! 390.230 !! 403.667&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 047 !! 408.388 !! 419.384&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 048 !! 36.138  !! 33.607&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 065 !! 301.346 !! 288.696&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 066 !! 75.162  !! 77.773&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 067 !! 231.737 !! 231.400&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 070 !! 87.586  !! 109.931&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 076 !! 50.321  !! 62.625&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 077 !! 490.394 !! 522.190&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 246.220 !! 251.686&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
===Summary===&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 320px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Sub Code&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg sBD&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg eBD&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! HW1 !! 220.805 !! 229.408&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12356</id>
		<title>2017:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12356"/>
		<updated>2017-10-25T15:37:32Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* General Legend */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
== General Legend ==&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; | Sub code&lt;br /&gt;
    ! width=&amp;quot;200&amp;quot; | Submission name&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; style=&amp;quot;text-align: center;&amp;quot; | Abstract&lt;br /&gt;
    ! width=&amp;quot;540&amp;quot; | Contributors&lt;br /&gt;
    |-&lt;br /&gt;
&lt;br /&gt;
    ! HW1&lt;br /&gt;
    | HW1  ||  style=&amp;quot;text-align: center;&amp;quot; |  Hao Wu || &lt;br /&gt;
    |-&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 001 !! 981.139 !! 990.869&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 002 !! 22.635 !!	18.241&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 024 !! 13.844 !!  25.790&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 036 !! 87.284  !!  106.569&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 043 !! 45.356 !! 68.930&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 069 !! 117.310  !! 132.401&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 073 !! 100.163 !! 107.107&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 195.390 !!  207.130&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 004 !! 85.503 !! 93.824&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 005 !! 788.662 !! 757.016&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 009 !! 130.044 !! 133.727&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 031 !! 125.346 !! 138.079&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 046 !! 390.230 !! 403.667&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 047 !! 408.388 !! 419.384&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 048 !! 36.138  !! 33.607&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 065 !! 301.346 !! 288.696&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 066 !! 75.162  !! 77.773&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 067 !! 231.737 !! 231.400&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 070 !! 87.586  !! 109.931&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 076 !! 50.321  !! 62.625&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 077 !! 490.394 !! 522.190&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 246.220 !! 251.686&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
===Summary===&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 320px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Sub Code&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg sBD&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg eBD&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! HW1 !! 220.805 !! 229.408&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12355</id>
		<title>2017:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12355"/>
		<updated>2017-10-25T08:19:37Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Summary */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
== General Legend ==&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; | Sub code&lt;br /&gt;
    ! width=&amp;quot;200&amp;quot; | Submission name&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; style=&amp;quot;text-align: center;&amp;quot; | Abstract&lt;br /&gt;
    ! width=&amp;quot;540&amp;quot; | Contributors&lt;br /&gt;
    |-&lt;br /&gt;
&lt;br /&gt;
    ! HW1&lt;br /&gt;
    | HW1  ||  style=&amp;quot;text-align: center;&amp;quot; |  || &lt;br /&gt;
    |-&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 001 !! 981.139 !! 990.869&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 002 !! 22.635 !!	18.241&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 024 !! 13.844 !!  25.790&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 036 !! 87.284  !!  106.569&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 043 !! 45.356 !! 68.930&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 069 !! 117.310  !! 132.401&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 073 !! 100.163 !! 107.107&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 195.390 !!  207.130&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 004 !! 85.503 !! 93.824&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 005 !! 788.662 !! 757.016&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 009 !! 130.044 !! 133.727&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 031 !! 125.346 !! 138.079&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 046 !! 390.230 !! 403.667&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 047 !! 408.388 !! 419.384&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 048 !! 36.138  !! 33.607&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 065 !! 301.346 !! 288.696&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 066 !! 75.162  !! 77.773&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 067 !! 231.737 !! 231.400&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 070 !! 87.586  !! 109.931&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 076 !! 50.321  !! 62.625&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 077 !! 490.394 !! 522.190&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 246.220 !! 251.686&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
===Summary===&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 320px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Sub Code&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg sBD&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg eBD&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! HW1 !! 220.805 !! 229.408&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12194</id>
		<title>2017:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12194"/>
		<updated>2017-10-09T16:24:02Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Testing Set */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
== General Legend ==&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; | Sub code&lt;br /&gt;
    ! width=&amp;quot;200&amp;quot; | Submission name&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; style=&amp;quot;text-align: center;&amp;quot; | Abstract&lt;br /&gt;
    ! width=&amp;quot;540&amp;quot; | Contributors&lt;br /&gt;
    |-&lt;br /&gt;
&lt;br /&gt;
    ! HW1&lt;br /&gt;
    | HW1  ||  style=&amp;quot;text-align: center;&amp;quot; |  || &lt;br /&gt;
    |-&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 001 !! 981.139 !! 990.869&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 002 !! 22.635 !!	18.241&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 024 !! 13.844 !!  25.790&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 036 !! 87.284  !!  106.569&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 043 !! 45.356 !! 68.930&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 069 !! 117.310  !! 132.401&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 073 !! 100.163 !! 107.107&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 195.390 !!  207.130&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 004 !! 85.503 !! 93.824&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 005 !! 788.662 !! 757.016&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 009 !! 130.044 !! 133.727&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 031 !! 125.346 !! 138.079&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 046 !! 390.230 !! 403.667&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 047 !! 408.388 !! 419.384&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 048 !! 36.138  !! 33.607&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 065 !! 301.346 !! 288.696&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 066 !! 75.162  !! 77.773&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 067 !! 231.737 !! 231.400&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 070 !! 87.586  !! 109.931&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 076 !! 50.321  !! 62.625&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 077 !! 490.394 !! 522.190&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 246.220 !! 251.686&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
===Summary===&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12193</id>
		<title>2017:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12193"/>
		<updated>2017-10-09T16:14:20Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Developing Set */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
== General Legend ==&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; | Sub code&lt;br /&gt;
    ! width=&amp;quot;200&amp;quot; | Submission name&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; style=&amp;quot;text-align: center;&amp;quot; | Abstract&lt;br /&gt;
    ! width=&amp;quot;540&amp;quot; | Contributors&lt;br /&gt;
    |-&lt;br /&gt;
&lt;br /&gt;
    ! HW1&lt;br /&gt;
    | HW1  ||  style=&amp;quot;text-align: center;&amp;quot; |  || &lt;br /&gt;
    |-&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 400px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=2 align=&amp;quot;center&amp;quot; | HW1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 001 !! 981.139 !! 990.869&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 002 !! 22.635 !!	18.241&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 024 !! 13.844 !!  25.790&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 036 !! 87.284  !!  106.569&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 043 !! 45.356 !! 68.930&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 069 !! 117.310  !! 132.401&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 073 !! 100.163 !! 107.107&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 195.390 !!  207.130&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Summary===&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12192</id>
		<title>2017:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12192"/>
		<updated>2017-10-09T15:23:25Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* General Legend */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
== General Legend ==&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; | Sub code&lt;br /&gt;
    ! width=&amp;quot;200&amp;quot; | Submission name&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; style=&amp;quot;text-align: center;&amp;quot; | Abstract&lt;br /&gt;
    ! width=&amp;quot;540&amp;quot; | Contributors&lt;br /&gt;
    |-&lt;br /&gt;
&lt;br /&gt;
    ! HW1&lt;br /&gt;
    | HW1  ||  style=&amp;quot;text-align: center;&amp;quot; |  || &lt;br /&gt;
    |-&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Summary===&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2017:MIREX2017_Results&amp;diff=12191</id>
		<title>2017:MIREX2017 Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2017:MIREX2017_Results&amp;diff=12191"/>
		<updated>2017-10-09T14:58:59Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Results by Task (More results are coming) */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;==Overall Results Poster==&lt;br /&gt;
Coming soon&lt;br /&gt;
&lt;br /&gt;
==Results by Task (More results are coming) ==&lt;br /&gt;
* [[2017:Audio Fingerprinting Results|Audio Fingerprinting Results]]&lt;br /&gt;
* [[2017:Set List Identification Results | Set List Identification Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12190</id>
		<title>2017:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2017:Set_List_Identification_Results&amp;diff=12190"/>
		<updated>2017-10-09T14:58:49Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: Created page with &amp;quot;== Introduction ==  Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''  ===Developing set Information=== This set contain 3 ar...&amp;quot;&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Summary===&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2016:Set_List_Identification_Results&amp;diff=11834</id>
		<title>2016:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2016:Set_List_Identification_Results&amp;diff=11834"/>
		<updated>2016-08-03T02:27:53Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* General Legend */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; | Sub Code &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; style=&amp;quot;text-align: center;&amp;quot; | Abstract &lt;br /&gt;
    ! width=&amp;quot;440&amp;quot; | Contributors&lt;br /&gt;
    |-&lt;br /&gt;
    ! YWYW1&lt;br /&gt;
    | style=&amp;quot;text-align: center;&amp;quot; | -- || Ming-Chi Yen, Ju-Chiang Wang, Yi-Hsuan Yang, Hsin-Min Wang&lt;br /&gt;
    |-&lt;br /&gt;
    ! YWJ1&lt;br /&gt;
    | style=&amp;quot;text-align: center;&amp;quot; | -- || Ming-Chi Yen, Hsin-Min Wang, Jyh-Shing Roger Jang&lt;br /&gt;
    |-&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW1&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWJ1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 001 !! 15 !!179.252 !! 176.876 !! 19 !! 179.252 !! 176.876&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 002 !! 12 !! 11.025 !! 21.615 !! 8 !! 11.025 !! 21.615&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 024 !! 4 !! 19.124 !! 22.848 !! 5 !! 19.124 !! 22.848&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 036 !! 18 !! 40.547 !! 49.772 !! 13 !! 40.547 !! 49.772&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 043 !! 13 !! 341.386 !! 427.867 !! 12 !! 341.386 !! 427.867&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 069 !! 16 !! 129.983 !! 162.558 !! 12 !! 129.983 !! 162.558&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 073 !! 13 !! 239.447 !! 309.902 !! 12 !! 239.447 !! 309.902&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 13 !! 137.252 !! 167.349 !! 11.57 !! 137.252 !! 167.349&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW1&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWJ1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 004 !! 6 !! 85.644 !! 33.271 !! 7 !! 85.644 !! 33.271&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 005 !! 20 !! 304.753 !! 413.590 !! 18 !! 304.753 !! 413.590&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 009 !! 13 !! 21.407 !! 66.230 !! 8 !! 21.407 !! 66.230&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 031 !! 10 !! 51.801 !! 71.234 !! 6 !! 51.801 !! 71.234&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 046 !! 5 !! 11.912 !! 24.883 !! 10 !! 11.912 !! 24.883&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 047 !! 9 !! 59.835 !! 36.959 !! 11 !! 59.835 !! 36.959&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 048 !! 14 !! 117.165 !! 125.612 !! 14 !! 117.165 !! 125.612&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 065 !! 7 !! 178.820 !! 255.402 !! 7 !! 178.820 !! 255.402&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 066 !! 9 !! 23.994 !! 23.699 !! 7 !! 23.994 !! 23.699&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 067 !! 11 !! 241.434 !! 301.096 !! 9 !! 241.434 !! 301.096&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 070 !! 12 !! 69.243 !! 96.336 !! 12 !! 69.243 !! 96.336&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 076 !! 7 !! 206.096 !! 315.669 !! 5 !! 206.096 !! 315.669&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 077 !! 13 !! 290.077 !! 278.479 !! 12 !! 290.077 !! 278.479&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 10.46 !! 127.860 !! 157.112 !! 9.69 !! 127.860 !! 157.112&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
===Summary===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 320px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Sub Code&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg ED&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg sBD&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg eBD&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! YWYW1 !! 11.35 !! 131.147 !! 160.695&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! YWJ1 !! 10.35 !! 131.147 !! 160.695&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2016:Set_List_Identification_Results&amp;diff=11833</id>
		<title>2016:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2016:Set_List_Identification_Results&amp;diff=11833"/>
		<updated>2016-08-03T02:27:38Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* General Legend */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; | Sub Code &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; style=&amp;quot;text-align: center;&amp;quot; | Abstract &lt;br /&gt;
    ! width=&amp;quot;440&amp;quot; | Contributors&lt;br /&gt;
    |-&lt;br /&gt;
    ! YWYW1&lt;br /&gt;
    | style=&amp;quot;text-align: center;&amp;quot; | -- || Ming-Chi Yen, Ju-Chiang Wang, Yi-Hsuan Yang, Hsin-Min Wang&lt;br /&gt;
    |-&lt;br /&gt;
    ! YWJ&lt;br /&gt;
    | style=&amp;quot;text-align: center;&amp;quot; | -- || Ming-Chi Yen, Hsin-Min Wang, Jyh-Shing Roger Jang&lt;br /&gt;
    |-&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW1&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWJ1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 001 !! 15 !!179.252 !! 176.876 !! 19 !! 179.252 !! 176.876&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 002 !! 12 !! 11.025 !! 21.615 !! 8 !! 11.025 !! 21.615&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 024 !! 4 !! 19.124 !! 22.848 !! 5 !! 19.124 !! 22.848&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 036 !! 18 !! 40.547 !! 49.772 !! 13 !! 40.547 !! 49.772&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 043 !! 13 !! 341.386 !! 427.867 !! 12 !! 341.386 !! 427.867&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 069 !! 16 !! 129.983 !! 162.558 !! 12 !! 129.983 !! 162.558&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 073 !! 13 !! 239.447 !! 309.902 !! 12 !! 239.447 !! 309.902&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 13 !! 137.252 !! 167.349 !! 11.57 !! 137.252 !! 167.349&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW1&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWJ1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 004 !! 6 !! 85.644 !! 33.271 !! 7 !! 85.644 !! 33.271&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 005 !! 20 !! 304.753 !! 413.590 !! 18 !! 304.753 !! 413.590&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 009 !! 13 !! 21.407 !! 66.230 !! 8 !! 21.407 !! 66.230&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 031 !! 10 !! 51.801 !! 71.234 !! 6 !! 51.801 !! 71.234&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 046 !! 5 !! 11.912 !! 24.883 !! 10 !! 11.912 !! 24.883&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 047 !! 9 !! 59.835 !! 36.959 !! 11 !! 59.835 !! 36.959&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 048 !! 14 !! 117.165 !! 125.612 !! 14 !! 117.165 !! 125.612&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 065 !! 7 !! 178.820 !! 255.402 !! 7 !! 178.820 !! 255.402&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 066 !! 9 !! 23.994 !! 23.699 !! 7 !! 23.994 !! 23.699&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 067 !! 11 !! 241.434 !! 301.096 !! 9 !! 241.434 !! 301.096&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 070 !! 12 !! 69.243 !! 96.336 !! 12 !! 69.243 !! 96.336&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 076 !! 7 !! 206.096 !! 315.669 !! 5 !! 206.096 !! 315.669&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 077 !! 13 !! 290.077 !! 278.479 !! 12 !! 290.077 !! 278.479&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 10.46 !! 127.860 !! 157.112 !! 9.69 !! 127.860 !! 157.112&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
===Summary===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 320px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Sub Code&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg ED&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg sBD&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg eBD&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! YWYW1 !! 11.35 !! 131.147 !! 160.695&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! YWJ1 !! 10.35 !! 131.147 !! 160.695&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2016:Set_List_Identification_Results&amp;diff=11795</id>
		<title>2016:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2016:Set_List_Identification_Results&amp;diff=11795"/>
		<updated>2016-07-31T16:26:57Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* General Legend */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; | Sub Code &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; style=&amp;quot;text-align: center;&amp;quot; | Abstract &lt;br /&gt;
    ! width=&amp;quot;440&amp;quot; | Contributors&lt;br /&gt;
    |-&lt;br /&gt;
    ! YWYW1&lt;br /&gt;
    | style=&amp;quot;text-align: center;&amp;quot; | [https://www.music-ir.org/mirex/abstracts/2015/YWYW1.pdf PDF] || Ming-Chi Yen, Ju-Chiang Wang, Yi-Hsuan Yang, Hsin-Min Wang&lt;br /&gt;
    |-&lt;br /&gt;
    ! YWJ&lt;br /&gt;
    | style=&amp;quot;text-align: center;&amp;quot; | [https://www.music-ir.org/mirex/abstracts/2015/YWYW2.pdf PDF] || Ming-Chi Yen, Hsin-Min Wang, Jyh-Shing Roger Jang&lt;br /&gt;
    |-&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW1&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWJ1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 001 !! 15 !!179.252 !! 176.876 !! 19 !! 179.252 !! 176.876&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 002 !! 12 !! 11.025 !! 21.615 !! 8 !! 11.025 !! 21.615&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 024 !! 4 !! 19.124 !! 22.848 !! 5 !! 19.124 !! 22.848&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 036 !! 18 !! 40.547 !! 49.772 !! 13 !! 40.547 !! 49.772&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 043 !! 13 !! 341.386 !! 427.867 !! 12 !! 341.386 !! 427.867&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 069 !! 16 !! 129.983 !! 162.558 !! 12 !! 129.983 !! 162.558&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 073 !! 13 !! 239.447 !! 309.902 !! 12 !! 239.447 !! 309.902&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 13 !! 137.252 !! 167.349 !! 11.57 !! 137.252 !! 167.349&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW1&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWJ1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 004 !! 6 !! 85.644 !! 33.271 !! 7 !! 85.644 !! 33.271&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 005 !! 20 !! 304.753 !! 413.590 !! 18 !! 304.753 !! 413.590&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 009 !! 13 !! 21.407 !! 66.230 !! 8 !! 21.407 !! 66.230&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 031 !! 10 !! 51.801 !! 71.234 !! 6 !! 51.801 !! 71.234&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 046 !! 5 !! 11.912 !! 24.883 !! 10 !! 11.912 !! 24.883&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 047 !! 9 !! 59.835 !! 36.959 !! 11 !! 59.835 !! 36.959&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 048 !! 14 !! 117.165 !! 125.612 !! 14 !! 117.165 !! 125.612&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 065 !! 7 !! 178.820 !! 255.402 !! 7 !! 178.820 !! 255.402&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 066 !! 9 !! 23.994 !! 23.699 !! 7 !! 23.994 !! 23.699&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 067 !! 11 !! 241.434 !! 301.096 !! 9 !! 241.434 !! 301.096&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 070 !! 12 !! 69.243 !! 96.336 !! 12 !! 69.243 !! 96.336&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 076 !! 7 !! 206.096 !! 315.669 !! 5 !! 206.096 !! 315.669&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 077 !! 13 !! 290.077 !! 278.479 !! 12 !! 290.077 !! 278.479&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 10.46 !! 127.860 !! 157.112 !! 9.69 !! 127.860 !! 157.112&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
===Summary===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 320px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Sub Code&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg ED&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg sBD&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg eBD&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! YWYW1 !! 11.35 !! 131.147 !! 160.695&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! YWJ1 !! 10.35 !! 131.147 !! 160.695&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2016:Set_List_Identification_Results&amp;diff=11794</id>
		<title>2016:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2016:Set_List_Identification_Results&amp;diff=11794"/>
		<updated>2016-07-31T16:25:45Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: Created page with &amp;quot;== Introduction ==  Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''  ===Developing set Information=== This set contain 3 ar...&amp;quot;&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; | Sub Code &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; style=&amp;quot;text-align: center;&amp;quot; | Abstract &lt;br /&gt;
    ! width=&amp;quot;440&amp;quot; | Contributors&lt;br /&gt;
    |-&lt;br /&gt;
    ! YWYW1&lt;br /&gt;
    | style=&amp;quot;text-align: center;&amp;quot; | [https://www.music-ir.org/mirex/abstracts/2015/YWYW1.pdf PDF] || [http://slam.iis.sinica.edu.tw/index.htm Ming-Chi Yen], [http://sovideo.iis.sinica.edu.tw/SLG/index.html Ju-Chiang Wang], [http://mpac.ee.ntu.edu.tw/~yihsuan/ Yi-Hsuan Yang], [http://www.iis.sinica.edu.tw Hsin-Min Wang]&lt;br /&gt;
    |-&lt;br /&gt;
    ! YWJ&lt;br /&gt;
    | style=&amp;quot;text-align: center;&amp;quot; | [https://www.music-ir.org/mirex/abstracts/2015/YWYW2.pdf PDF] || [http://slam.iis.sinica.edu.tw/index.htm Ming-Chi Yen],   [http://www.iis.sinica.edu.tw Hsin-Min Wang], Jyh-Shing Roger Jang&lt;br /&gt;
    |-&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW1&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWJ1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 001 !! 15 !!179.252 !! 176.876 !! 19 !! 179.252 !! 176.876&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 002 !! 12 !! 11.025 !! 21.615 !! 8 !! 11.025 !! 21.615&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 024 !! 4 !! 19.124 !! 22.848 !! 5 !! 19.124 !! 22.848&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 036 !! 18 !! 40.547 !! 49.772 !! 13 !! 40.547 !! 49.772&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 043 !! 13 !! 341.386 !! 427.867 !! 12 !! 341.386 !! 427.867&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 069 !! 16 !! 129.983 !! 162.558 !! 12 !! 129.983 !! 162.558&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 073 !! 13 !! 239.447 !! 309.902 !! 12 !! 239.447 !! 309.902&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 13 !! 137.252 !! 167.349 !! 11.57 !! 137.252 !! 167.349&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW1&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWJ1&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 004 !! 6 !! 85.644 !! 33.271 !! 7 !! 85.644 !! 33.271&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 005 !! 20 !! 304.753 !! 413.590 !! 18 !! 304.753 !! 413.590&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 009 !! 13 !! 21.407 !! 66.230 !! 8 !! 21.407 !! 66.230&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 031 !! 10 !! 51.801 !! 71.234 !! 6 !! 51.801 !! 71.234&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 046 !! 5 !! 11.912 !! 24.883 !! 10 !! 11.912 !! 24.883&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 047 !! 9 !! 59.835 !! 36.959 !! 11 !! 59.835 !! 36.959&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 048 !! 14 !! 117.165 !! 125.612 !! 14 !! 117.165 !! 125.612&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 065 !! 7 !! 178.820 !! 255.402 !! 7 !! 178.820 !! 255.402&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 066 !! 9 !! 23.994 !! 23.699 !! 7 !! 23.994 !! 23.699&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 067 !! 11 !! 241.434 !! 301.096 !! 9 !! 241.434 !! 301.096&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 070 !! 12 !! 69.243 !! 96.336 !! 12 !! 69.243 !! 96.336&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 076 !! 7 !! 206.096 !! 315.669 !! 5 !! 206.096 !! 315.669&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 077 !! 13 !! 290.077 !! 278.479 !! 12 !! 290.077 !! 278.479&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 10.46 !! 127.860 !! 157.112 !! 9.69 !! 127.860 !! 157.112&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
===Summary===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 320px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Sub Code&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg ED&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg sBD&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg eBD&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! YWYW1 !! 11.35 !! 131.147 !! 160.695&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! YWJ1 !! 10.35 !! 131.147 !! 160.695&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification_Results&amp;diff=11529</id>
		<title>2015:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification_Results&amp;diff=11529"/>
		<updated>2015-10-21T07:35:29Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* General Legend */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; | Sub Code &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; style=&amp;quot;text-align: center;&amp;quot; | Abstract &lt;br /&gt;
    ! width=&amp;quot;440&amp;quot; | Contributors&lt;br /&gt;
    |-&lt;br /&gt;
    ! YWYW1&lt;br /&gt;
    | style=&amp;quot;text-align: center;&amp;quot; | [https://www.music-ir.org/mirex/abstracts/2015/YWYW1.pdf PDF] || [http://slam.iis.sinica.edu.tw/index.htm Ming-Chi Yen], [http://sovideo.iis.sinica.edu.tw/SLG/index.html Ju-Chiang Wang], [http://mpac.ee.ntu.edu.tw/~yihsuan/ Yi-Hsuan Yang], [http://www.iis.sinica.edu.tw Hsin-Min Wang]&lt;br /&gt;
    |-&lt;br /&gt;
    ! YWYW2&lt;br /&gt;
    | style=&amp;quot;text-align: center;&amp;quot; | [https://www.music-ir.org/mirex/abstracts/2015/YWYW2.pdf PDF] || [http://slam.iis.sinica.edu.tw/index.htm Ming-Chi Yen], [http://sovideo.iis.sinica.edu.tw/SLG/index.html Ju-Chiang Wang], [http://mpac.ee.ntu.edu.tw/~yihsuan/ Yi-Hsuan Yang], [http://www.iis.sinica.edu.tw Hsin-Min Wang]&lt;br /&gt;
    |-&lt;br /&gt;
    ! YWYW3&lt;br /&gt;
    | style=&amp;quot;text-align: center;&amp;quot; | [https://www.music-ir.org/mirex/abstracts/2015/YWYW3.pdf PDF] || [http://slam.iis.sinica.edu.tw/index.htm Ming-Chi Yen], [http://sovideo.iis.sinica.edu.tw/SLG/index.html Ju-Chiang Wang], [http://mpac.ee.ntu.edu.tw/~yihsuan/ Yi-Hsuan Yang], [http://www.iis.sinica.edu.tw Hsin-Min Wang]&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW1&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW2&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW3&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 001 !! 15 !!179.252 !! 176.876 !! 19 !! 179.252 !! 176.876 !! 20 !! 1718.929 !! 1636.810&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 002 !! 12 !! 11.025 !! 21.615 !! 8 !! 11.025 !! 21.615 !! 8 !! 12.157 !! 15.076&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 024 !! 4 !! 19.124 !! 22.848 !! 5 !! 19.124 !! 22.848 !! 3 !! 108.565 !! 52.557&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 036 !! 18 !! 40.547 !! 49.772 !! 13 !! 40.547 !! 49.772 !! 12 !! 67.756 !! 59.672&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 043 !! 13 !! 341.386 !! 427.867 !! 12 !! 341.386 !! 427.867 !! 17 !! 284.778 !! 346.389&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 069 !! 16 !! 129.983 !! 162.558 !! 12 !! 129.983 !! 162.558 !! 12 !! 83.048 !! 42.002&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 073 !! 13 !! 239.447 !! 309.902 !! 12 !! 239.447 !! 309.902 !! 16 !! 63.693 !! 95.713&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 13 !! 137.252 !! 167.349 !! 11.57 !! 137.252 !! 167.349 !! 12.57 !! 334.132 !! 321.174&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW1&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW2&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW3&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 004 !! 6 !! 85.644 !! 33.271 !! 7 !! 85.644 !! 33.271 !! 8 !! 490.658 !! 445.986&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 005 !! 20 !! 304.753 !! 413.590 !! 18 !! 304.753 !! 413.590 !! 16 !! 144.300 !! 185.604&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 009 !! 13 !! 21.407 !! 66.230 !! 8 !! 21.407 !! 66.230 !! 11 !! 38.930 !! 51.577&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 031 !! 10 !! 51.801 !! 71.234 !! 6 !! 51.801 !! 71.234 !! 8 !! 117.670 !! 63.418&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 046 !! 5 !! 11.912 !! 24.883 !! 10 !! 11.912 !! 24.883 !! 13 !! 840.530 !! 818.607&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 047 !! 9 !! 59.835 !! 36.959 !! 11 !! 59.835 !! 36.959 !! 18 !! 195.221 !! 131.040&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 048 !! 14 !! 117.165 !! 125.612 !! 14 !! 117.165 !! 125.612 !! 14 !! 132.044 !! 157.874&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 065 !! 7 !! 178.820 !! 255.402 !! 7 !! 178.820 !! 255.402 !! 6 !! 155.572 !! 227.516&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 066 !! 9 !! 23.994 !! 23.699 !! 7 !! 23.994 !! 23.699 !! 8 !! 1371.639 !! 1372.828&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 067 !! 11 !! 241.434 !! 301.096 !! 9 !! 241.434 !! 301.096 !! 9 !! 107.313 !! 93.293&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 070 !! 12 !! 69.243 !! 96.336 !! 12 !! 69.243 !! 96.336 !! 11 !! 80.615 !! 98.123&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 076 !! 7 !! 206.096 !! 315.669 !! 5 !! 206.096 !! 315.669 !! 7 !! 128.045 !! 78.691&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 077 !! 13 !! 290.077 !! 278.479 !! 12 !! 290.077 !! 278.479 !! 13 !! 315.441 !! 290.992&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 10.46 !! 127.860 !! 157.112 !! 9.69 !! 127.860 !! 157.112 !! 10.92 !! 316.768 !! 308.888&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
===Summary===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 320px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Sub Code&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg ED&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg sBD&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg eBD&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! YWYW1 !! 11.35 !! 131.147 !! 160.695&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! YWYW2 !! 10.35 !! 131.147 !! 160.695&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! YWYW3 !! 11.50 !! 322.845 !! 313.188&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification_Results&amp;diff=11528</id>
		<title>2015:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification_Results&amp;diff=11528"/>
		<updated>2015-10-21T07:35:06Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* General Legend */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; | Sub code &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; style=&amp;quot;text-align: center;&amp;quot; | Abstract &lt;br /&gt;
    ! width=&amp;quot;440&amp;quot; | Contributors&lt;br /&gt;
    |-&lt;br /&gt;
    ! YWYW1&lt;br /&gt;
    | style=&amp;quot;text-align: center;&amp;quot; | [https://www.music-ir.org/mirex/abstracts/2015/YWYW1.pdf PDF] || [http://slam.iis.sinica.edu.tw/index.htm Ming-Chi Yen], [http://sovideo.iis.sinica.edu.tw/SLG/index.html Ju-Chiang Wang], [http://mpac.ee.ntu.edu.tw/~yihsuan/ Yi-Hsuan Yang], [http://www.iis.sinica.edu.tw Hsin-Min Wang]&lt;br /&gt;
    |-&lt;br /&gt;
    ! YWYW2&lt;br /&gt;
    | style=&amp;quot;text-align: center;&amp;quot; | [https://www.music-ir.org/mirex/abstracts/2015/YWYW2.pdf PDF] || [http://slam.iis.sinica.edu.tw/index.htm Ming-Chi Yen], [http://sovideo.iis.sinica.edu.tw/SLG/index.html Ju-Chiang Wang], [http://mpac.ee.ntu.edu.tw/~yihsuan/ Yi-Hsuan Yang], [http://www.iis.sinica.edu.tw Hsin-Min Wang]&lt;br /&gt;
    |-&lt;br /&gt;
    ! YWYW3&lt;br /&gt;
    | style=&amp;quot;text-align: center;&amp;quot; | [https://www.music-ir.org/mirex/abstracts/2015/YWYW3.pdf PDF] || [http://slam.iis.sinica.edu.tw/index.htm Ming-Chi Yen], [http://sovideo.iis.sinica.edu.tw/SLG/index.html Ju-Chiang Wang], [http://mpac.ee.ntu.edu.tw/~yihsuan/ Yi-Hsuan Yang], [http://www.iis.sinica.edu.tw Hsin-Min Wang]&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW1&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW2&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW3&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 001 !! 15 !!179.252 !! 176.876 !! 19 !! 179.252 !! 176.876 !! 20 !! 1718.929 !! 1636.810&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 002 !! 12 !! 11.025 !! 21.615 !! 8 !! 11.025 !! 21.615 !! 8 !! 12.157 !! 15.076&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 024 !! 4 !! 19.124 !! 22.848 !! 5 !! 19.124 !! 22.848 !! 3 !! 108.565 !! 52.557&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 036 !! 18 !! 40.547 !! 49.772 !! 13 !! 40.547 !! 49.772 !! 12 !! 67.756 !! 59.672&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 043 !! 13 !! 341.386 !! 427.867 !! 12 !! 341.386 !! 427.867 !! 17 !! 284.778 !! 346.389&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 069 !! 16 !! 129.983 !! 162.558 !! 12 !! 129.983 !! 162.558 !! 12 !! 83.048 !! 42.002&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 073 !! 13 !! 239.447 !! 309.902 !! 12 !! 239.447 !! 309.902 !! 16 !! 63.693 !! 95.713&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 13 !! 137.252 !! 167.349 !! 11.57 !! 137.252 !! 167.349 !! 12.57 !! 334.132 !! 321.174&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW1&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW2&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW3&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 004 !! 6 !! 85.644 !! 33.271 !! 7 !! 85.644 !! 33.271 !! 8 !! 490.658 !! 445.986&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 005 !! 20 !! 304.753 !! 413.590 !! 18 !! 304.753 !! 413.590 !! 16 !! 144.300 !! 185.604&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 009 !! 13 !! 21.407 !! 66.230 !! 8 !! 21.407 !! 66.230 !! 11 !! 38.930 !! 51.577&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 031 !! 10 !! 51.801 !! 71.234 !! 6 !! 51.801 !! 71.234 !! 8 !! 117.670 !! 63.418&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 046 !! 5 !! 11.912 !! 24.883 !! 10 !! 11.912 !! 24.883 !! 13 !! 840.530 !! 818.607&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 047 !! 9 !! 59.835 !! 36.959 !! 11 !! 59.835 !! 36.959 !! 18 !! 195.221 !! 131.040&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 048 !! 14 !! 117.165 !! 125.612 !! 14 !! 117.165 !! 125.612 !! 14 !! 132.044 !! 157.874&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 065 !! 7 !! 178.820 !! 255.402 !! 7 !! 178.820 !! 255.402 !! 6 !! 155.572 !! 227.516&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 066 !! 9 !! 23.994 !! 23.699 !! 7 !! 23.994 !! 23.699 !! 8 !! 1371.639 !! 1372.828&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 067 !! 11 !! 241.434 !! 301.096 !! 9 !! 241.434 !! 301.096 !! 9 !! 107.313 !! 93.293&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 070 !! 12 !! 69.243 !! 96.336 !! 12 !! 69.243 !! 96.336 !! 11 !! 80.615 !! 98.123&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 076 !! 7 !! 206.096 !! 315.669 !! 5 !! 206.096 !! 315.669 !! 7 !! 128.045 !! 78.691&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 077 !! 13 !! 290.077 !! 278.479 !! 12 !! 290.077 !! 278.479 !! 13 !! 315.441 !! 290.992&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 10.46 !! 127.860 !! 157.112 !! 9.69 !! 127.860 !! 157.112 !! 10.92 !! 316.768 !! 308.888&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
===Summary===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 320px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Sub Code&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg ED&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg sBD&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg eBD&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! YWYW1 !! 11.35 !! 131.147 !! 160.695&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! YWYW2 !! 10.35 !! 131.147 !! 160.695&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! YWYW3 !! 11.50 !! 322.845 !! 313.188&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification_Results&amp;diff=11527</id>
		<title>2015:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification_Results&amp;diff=11527"/>
		<updated>2015-10-21T07:29:42Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: &lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; | Sub code &lt;br /&gt;
    ! width=&amp;quot;200&amp;quot; | Submission name &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; style=&amp;quot;text-align: center;&amp;quot; | Abstract &lt;br /&gt;
    ! width=&amp;quot;440&amp;quot; | Contributors&lt;br /&gt;
    |-&lt;br /&gt;
    ! YWYW1&lt;br /&gt;
    | 	YWYW ||  style=&amp;quot;text-align: center;&amp;quot; | [https://www.music-ir.org/mirex/abstracts/2015/YWYW1.pdf PDF] || [http://slam.iis.sinica.edu.tw/index.htm Ming-Chi Yen], [http://sovideo.iis.sinica.edu.tw/SLG/index.html Ju-Chiang Wang], [http://mpac.ee.ntu.edu.tw/~yihsuan/ Yi-Hsuan Yang], [http://www.iis.sinica.edu.tw Hsin-Min Wang]&lt;br /&gt;
    |-&lt;br /&gt;
    ! YWYW2&lt;br /&gt;
    | 	YWYW ||  style=&amp;quot;text-align: center;&amp;quot; | [https://www.music-ir.org/mirex/abstracts/2015/YWYW2.pdf PDF] || [http://slam.iis.sinica.edu.tw/index.htm Ming-Chi Yen], [http://sovideo.iis.sinica.edu.tw/SLG/index.html Ju-Chiang Wang], [http://mpac.ee.ntu.edu.tw/~yihsuan/ Yi-Hsuan Yang], [http://www.iis.sinica.edu.tw Hsin-Min Wang]&lt;br /&gt;
    |-&lt;br /&gt;
    ! YWYW3&lt;br /&gt;
    | 	YWYW ||  style=&amp;quot;text-align: center;&amp;quot; | [https://www.music-ir.org/mirex/abstracts/2015/YWYW3.pdf PDF] || [http://slam.iis.sinica.edu.tw/index.htm Ming-Chi Yen], [http://sovideo.iis.sinica.edu.tw/SLG/index.html Ju-Chiang Wang], [http://mpac.ee.ntu.edu.tw/~yihsuan/ Yi-Hsuan Yang], [http://www.iis.sinica.edu.tw Hsin-Min Wang]&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW1&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW2&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW3&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 001 !! 15 !!179.252 !! 176.876 !! 19 !! 179.252 !! 176.876 !! 20 !! 1718.929 !! 1636.810&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 002 !! 12 !! 11.025 !! 21.615 !! 8 !! 11.025 !! 21.615 !! 8 !! 12.157 !! 15.076&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 024 !! 4 !! 19.124 !! 22.848 !! 5 !! 19.124 !! 22.848 !! 3 !! 108.565 !! 52.557&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 036 !! 18 !! 40.547 !! 49.772 !! 13 !! 40.547 !! 49.772 !! 12 !! 67.756 !! 59.672&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 043 !! 13 !! 341.386 !! 427.867 !! 12 !! 341.386 !! 427.867 !! 17 !! 284.778 !! 346.389&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 069 !! 16 !! 129.983 !! 162.558 !! 12 !! 129.983 !! 162.558 !! 12 !! 83.048 !! 42.002&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 073 !! 13 !! 239.447 !! 309.902 !! 12 !! 239.447 !! 309.902 !! 16 !! 63.693 !! 95.713&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 13 !! 137.252 !! 167.349 !! 11.57 !! 137.252 !! 167.349 !! 12.57 !! 334.132 !! 321.174&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; |&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW1&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW2&lt;br /&gt;
    ! colspan=3 align=&amp;quot;center&amp;quot; | YWYW3&lt;br /&gt;
    |-&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | Concert ID  &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | ED&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | sBD&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; align=&amp;quot;center&amp;quot; | eBD&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 004 !! 6 !! 85.644 !! 33.271 !! 7 !! 85.644 !! 33.271 !! 8 !! 490.658 !! 445.986&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 005 !! 20 !! 304.753 !! 413.590 !! 18 !! 304.753 !! 413.590 !! 16 !! 144.300 !! 185.604&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 009 !! 13 !! 21.407 !! 66.230 !! 8 !! 21.407 !! 66.230 !! 11 !! 38.930 !! 51.577&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 031 !! 10 !! 51.801 !! 71.234 !! 6 !! 51.801 !! 71.234 !! 8 !! 117.670 !! 63.418&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 046 !! 5 !! 11.912 !! 24.883 !! 10 !! 11.912 !! 24.883 !! 13 !! 840.530 !! 818.607&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 047 !! 9 !! 59.835 !! 36.959 !! 11 !! 59.835 !! 36.959 !! 18 !! 195.221 !! 131.040&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 048 !! 14 !! 117.165 !! 125.612 !! 14 !! 117.165 !! 125.612 !! 14 !! 132.044 !! 157.874&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 065 !! 7 !! 178.820 !! 255.402 !! 7 !! 178.820 !! 255.402 !! 6 !! 155.572 !! 227.516&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 066 !! 9 !! 23.994 !! 23.699 !! 7 !! 23.994 !! 23.699 !! 8 !! 1371.639 !! 1372.828&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 067 !! 11 !! 241.434 !! 301.096 !! 9 !! 241.434 !! 301.096 !! 9 !! 107.313 !! 93.293&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 070 !! 12 !! 69.243 !! 96.336 !! 12 !! 69.243 !! 96.336 !! 11 !! 80.615 !! 98.123&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 076 !! 7 !! 206.096 !! 315.669 !! 5 !! 206.096 !! 315.669 !! 7 !! 128.045 !! 78.691&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! 077 !! 13 !! 290.077 !! 278.479 !! 12 !! 290.077 !! 278.479 !! 13 !! 315.441 !! 290.992&lt;br /&gt;
    |-align=&amp;quot;right&amp;quot;&lt;br /&gt;
    ! Avg !! 10.46 !! 127.860 !! 157.112 !! 9.69 !! 127.860 !! 157.112 !! 10.92 !! 316.768 !! 308.888&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
===Summary===&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 320px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Sub Code&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg ED&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg sBD&lt;br /&gt;
! width=&amp;quot;80&amp;quot; | Avg eBD&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! YWYW1 !! 11.35 !! 131.147 !! 160.695&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! YWYW2 !! 10.35 !! 131.147 !! 160.695&lt;br /&gt;
|-align=&amp;quot;right&amp;quot;&lt;br /&gt;
! YWYW3 !! 11.50 !! 322.845 !! 313.188&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification_Results&amp;diff=11526</id>
		<title>2015:Set List Identification Results</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification_Results&amp;diff=11526"/>
		<updated>2015-10-21T06:47:54Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: Created page with &amp;quot;== Introduction ==  Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''  ===Developing set Information=== This set contain 3 ar...&amp;quot;&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;== Introduction ==&lt;br /&gt;
&lt;br /&gt;
Set List Identification was evaluated against on two data sets: ''Developing set'' and ''Testing set''&lt;br /&gt;
&lt;br /&gt;
===Developing set Information===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set Information===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
== General Legend ==&lt;br /&gt;
{| border=&amp;quot;1&amp;quot; cellspacing=&amp;quot;0&amp;quot; style=&amp;quot;text-align: left; width: 800px;&amp;quot;&lt;br /&gt;
    |- style=&amp;quot;background: yellow;&amp;quot;&lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; | Sub code &lt;br /&gt;
    ! width=&amp;quot;200&amp;quot; | Submission name &lt;br /&gt;
    ! width=&amp;quot;80&amp;quot; style=&amp;quot;text-align: center;&amp;quot; | Abstract &lt;br /&gt;
    ! width=&amp;quot;440&amp;quot; | Contributors&lt;br /&gt;
    |-&lt;br /&gt;
    ! YWYW1&lt;br /&gt;
    | 	YWYW ||  style=&amp;quot;text-align: center;&amp;quot; | [https://www.music-ir.org/mirex/abstracts/2015/YWYW1.pdf PDF] || [http://slam.iis.sinica.edu.tw/index.htm Ming-Chi Yen], [http://sovideo.iis.sinica.edu.tw/SLG/index.html Ju-Chiang Wang], [http://mpac.ee.ntu.edu.tw/~yihsuan/ Yi-Hsuan Yang], [http://www.iis.sinica.edu.tw Hsin-Min Wang]&lt;br /&gt;
    |-&lt;br /&gt;
    ! YWYW2&lt;br /&gt;
    | 	YWYW ||  style=&amp;quot;text-align: center;&amp;quot; | [https://www.music-ir.org/mirex/abstracts/2015/YWYW2.pdf PDF] || [http://slam.iis.sinica.edu.tw/index.htm Ming-Chi Yen], [http://sovideo.iis.sinica.edu.tw/SLG/index.html Ju-Chiang Wang], [http://mpac.ee.ntu.edu.tw/~yihsuan/ Yi-Hsuan Yang], [http://www.iis.sinica.edu.tw Hsin-Min Wang]&lt;br /&gt;
    |-&lt;br /&gt;
    ! YWYW3&lt;br /&gt;
    | 	YWYW ||  style=&amp;quot;text-align: center;&amp;quot; | [https://www.music-ir.org/mirex/abstracts/2015/YWYW3.pdf PDF] || [http://slam.iis.sinica.edu.tw/index.htm Ming-Chi Yen], [http://sovideo.iis.sinica.edu.tw/SLG/index.html Ju-Chiang Wang], [http://mpac.ee.ntu.edu.tw/~yihsuan/ Yi-Hsuan Yang], [http://www.iis.sinica.edu.tw Hsin-Min Wang]&lt;br /&gt;
&lt;br /&gt;
|}&lt;br /&gt;
&lt;br /&gt;
== Results ==&lt;br /&gt;
&lt;br /&gt;
===Developing Set ===&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
=== Testing Set ===&lt;br /&gt;
&lt;br /&gt;
===Mixed Set===&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
[[Category: Results]]&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11203</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11203"/>
		<updated>2015-08-12T07:40:00Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Sub task 1 */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [https://www.music-ir.org/mirex/wiki/2015:Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time boundaries as follow: average start time boundary and average end time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
* Set list contains '''&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;''' songs&lt;br /&gt;
&lt;br /&gt;
''' Ground truth: '''&lt;br /&gt;
&lt;br /&gt;
* Start time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;sBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;eBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
''' Identification result: ''' &lt;br /&gt;
&lt;br /&gt;
* Start time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;sBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;eBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGsBD =\frac{\sum_{i=1}^N |sBD_{GT_i} - sBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGeBD =\frac{\sum_{i=1}^N |eBD_{GT_i} - eBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
Two inputs : live file list and studio song file list&lt;br /&gt;
&lt;br /&gt;
One output: song ID sequence&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
&lt;br /&gt;
Three inputs : song ID sequence list, live file list and studio song file list&lt;br /&gt;
&lt;br /&gt;
One output: time label of song list&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  (for input input sond ID:3)&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  (for input input sond ID:17)&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  (for input input sond ID:59)&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11202</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11202"/>
		<updated>2015-08-12T07:39:50Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Sub task 2 */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [https://www.music-ir.org/mirex/wiki/2015:Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time boundaries as follow: average start time boundary and average end time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
* Set list contains '''&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;''' songs&lt;br /&gt;
&lt;br /&gt;
''' Ground truth: '''&lt;br /&gt;
&lt;br /&gt;
* Start time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;sBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;eBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
''' Identification result: ''' &lt;br /&gt;
&lt;br /&gt;
* Start time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;sBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;eBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGsBD =\frac{\sum_{i=1}^N |sBD_{GT_i} - sBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGeBD =\frac{\sum_{i=1}^N |eBD_{GT_i} - eBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
Two inputs : live file list and studio song file list&lt;br /&gt;
&lt;br /&gt;
One out put: song ID sequence&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
&lt;br /&gt;
Three inputs : song ID sequence list, live file list and studio song file list&lt;br /&gt;
&lt;br /&gt;
One output: time label of song list&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  (for input input sond ID:3)&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  (for input input sond ID:17)&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  (for input input sond ID:59)&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11201</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11201"/>
		<updated>2015-08-12T07:06:38Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Submission Format */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [https://www.music-ir.org/mirex/wiki/2015:Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time boundaries as follow: average start time boundary and average end time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
* Set list contains '''&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;''' songs&lt;br /&gt;
&lt;br /&gt;
''' Ground truth: '''&lt;br /&gt;
&lt;br /&gt;
* Start time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;sBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;eBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
''' Identification result: ''' &lt;br /&gt;
&lt;br /&gt;
* Start time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;sBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;eBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGsBD =\frac{\sum_{i=1}^N |sBD_{GT_i} - sBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGeBD =\frac{\sum_{i=1}^N |eBD_{GT_i} - eBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
Two inputs : live file list and studio song file list&lt;br /&gt;
&lt;br /&gt;
One out put: song ID sequence&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
&lt;br /&gt;
Three inputs : song ID sequence list, live file list and studio song file list&lt;br /&gt;
&lt;br /&gt;
One out put: time label of song list&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  (for input input sond ID:3)&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  (for input input sond ID:17)&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  (for input input sond ID:59)&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11200</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11200"/>
		<updated>2015-08-12T06:44:28Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Submission Format */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [https://www.music-ir.org/mirex/wiki/2015:Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time boundaries as follow: average start time boundary and average end time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
* Set list contains '''&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;''' songs&lt;br /&gt;
&lt;br /&gt;
''' Ground truth: '''&lt;br /&gt;
&lt;br /&gt;
* Start time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;sBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;eBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
''' Identification result: ''' &lt;br /&gt;
&lt;br /&gt;
* Start time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;sBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;eBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGsBD =\frac{\sum_{i=1}^N |sBD_{GT_i} - sBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGeBD =\frac{\sum_{i=1}^N |eBD_{GT_i} - eBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
Two inputs : live file list and studio song file list&lt;br /&gt;
&lt;br /&gt;
One out put: song ID sequence&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
&lt;br /&gt;
Two inputs : song ID sequence list and studio song file list&lt;br /&gt;
&lt;br /&gt;
One out put: time label of song list&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/this_concert/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/this_concert/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/this_concert/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  (for input input sond ID:3)&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  (for input input sond ID:17)&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  (for input input sond ID:59)&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11190</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11190"/>
		<updated>2015-08-02T07:15:55Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Developing set */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [https://www.music-ir.org/mirex/wiki/2015:Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time boundaries as follow: average start time boundary and average end time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
* Set list contains '''&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;''' songs&lt;br /&gt;
&lt;br /&gt;
''' Ground truth: '''&lt;br /&gt;
&lt;br /&gt;
* Start time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;sBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;eBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
''' Identification result: ''' &lt;br /&gt;
&lt;br /&gt;
* Start time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;sBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;eBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGsBD =\frac{\sum_{i=1}^N |sBD_{GT_i} - sBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGeBD =\frac{\sum_{i=1}^N |eBD_{GT_i} - eBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11189</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11189"/>
		<updated>2015-08-02T07:15:31Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Developing set */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [https://www.music-ir.org/mirex/wiki/2015:Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([[https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox] Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time boundaries as follow: average start time boundary and average end time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
* Set list contains '''&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;''' songs&lt;br /&gt;
&lt;br /&gt;
''' Ground truth: '''&lt;br /&gt;
&lt;br /&gt;
* Start time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;sBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;eBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
''' Identification result: ''' &lt;br /&gt;
&lt;br /&gt;
* Start time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;sBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;eBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGsBD =\frac{\sum_{i=1}^N |sBD_{GT_i} - sBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGeBD =\frac{\sum_{i=1}^N |eBD_{GT_i} - eBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11188</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11188"/>
		<updated>2015-07-31T09:26:54Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Developing set */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [https://www.music-ir.org/mirex/wiki/2015:Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. (TBD)&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time boundaries as follow: average start time boundary and average end time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
* Set list contains '''&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;''' songs&lt;br /&gt;
&lt;br /&gt;
''' Ground truth: '''&lt;br /&gt;
&lt;br /&gt;
* Start time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;sBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;eBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
''' Identification result: ''' &lt;br /&gt;
&lt;br /&gt;
* Start time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;sBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;eBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGsBD =\frac{\sum_{i=1}^N |sBD_{GT_i} - sBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGeBD =\frac{\sum_{i=1}^N |eBD_{GT_i} - eBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11187</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11187"/>
		<updated>2015-07-31T09:21:00Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Developing set */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [https://www.music-ir.org/mirex/wiki/2015:Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. ([https://www.dropbox.com/s/bote36k8pkmt2f8/MIREX_2015_Setlist_ID_Developing_set_chroma_fea.rar?dl=0 Dropbox])&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time boundaries as follow: average start time boundary and average end time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
* Set list contains '''&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;''' songs&lt;br /&gt;
&lt;br /&gt;
''' Ground truth: '''&lt;br /&gt;
&lt;br /&gt;
* Start time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;sBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;eBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
''' Identification result: ''' &lt;br /&gt;
&lt;br /&gt;
* Start time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;sBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;eBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGsBD =\frac{\sum_{i=1}^N |sBD_{GT_i} - sBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGeBD =\frac{\sum_{i=1}^N |eBD_{GT_i} - eBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11172</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11172"/>
		<updated>2015-07-28T18:52:32Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Data */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [https://www.music-ir.org/mirex/wiki/2015:Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. (TBC)&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time boundaries as follow: average start time boundary and average end time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
* Set list contains '''&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;''' songs&lt;br /&gt;
&lt;br /&gt;
''' Ground truth: '''&lt;br /&gt;
&lt;br /&gt;
* Start time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;sBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;eBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
''' Identification result: ''' &lt;br /&gt;
&lt;br /&gt;
* Start time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;sBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;eBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGsBD =\frac{\sum_{i=1}^N |sBD_{GT_i} - sBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGeBD =\frac{\sum_{i=1}^N |eBD_{GT_i} - eBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11044</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11044"/>
		<updated>2015-07-14T08:54:58Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Sub task 2 */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [http://140.109.22.101/MediaWiki/index.php?title=Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. (TBC)&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time boundaries as follow: average start time boundary and average end time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
* Set list contains '''&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;''' songs&lt;br /&gt;
&lt;br /&gt;
''' Ground truth: '''&lt;br /&gt;
&lt;br /&gt;
* Start time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;sBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;eBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
''' Identification result: ''' &lt;br /&gt;
&lt;br /&gt;
* Start time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;sBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song '''&amp;lt;math&amp;gt;i&amp;lt;/math&amp;gt;'''：&amp;lt;math&amp;gt;eBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGsBD =\frac{\sum_{i=1}^N |sBD_{GT_i} - sBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGeBD =\frac{\sum_{i=1}^N |eBD_{GT_i} - eBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11043</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11043"/>
		<updated>2015-07-14T08:54:09Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Sub task 2 */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [http://140.109.22.101/MediaWiki/index.php?title=Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. (TBC)&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time boundaries as follow: average start time boundary and average end time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
* Set list contains '''&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;''' songs&lt;br /&gt;
&lt;br /&gt;
''' Ground truth: '''&lt;br /&gt;
&lt;br /&gt;
* Start time of song i：&amp;lt;math&amp;gt;sBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song i：&amp;lt;math&amp;gt;eBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
''' Identification result: ''' &lt;br /&gt;
&lt;br /&gt;
* Start time of song i：&amp;lt;math&amp;gt;sBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song i：&amp;lt;math&amp;gt;eBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGsBD =\frac{\sum_{i=1}^N |sBD_{GT_i} - sBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGeBD =\frac{\sum_{i=1}^N |eBD_{GT_i} - eBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11042</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11042"/>
		<updated>2015-07-14T08:53:11Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Sub task 2 */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [http://140.109.22.101/MediaWiki/index.php?title=Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. (TBC)&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time boundaries as follow: average start time boundary and average end time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
* Set list contains &amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt; songs&lt;br /&gt;
&lt;br /&gt;
''' Ground truth: '''&lt;br /&gt;
&lt;br /&gt;
* Start time of song i：&amp;lt;math&amp;gt;sBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song i：&amp;lt;math&amp;gt;eBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
''' Identification result: ''' &lt;br /&gt;
&lt;br /&gt;
* Start time of song i：&amp;lt;math&amp;gt;sBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song i：&amp;lt;math&amp;gt;eBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGsBD =\frac{\sum_{i=1}^N |sBD_{GT_i} - sBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGeBD =\frac{\sum_{i=1}^N |eBD_{GT_i} - eBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11041</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11041"/>
		<updated>2015-07-14T08:52:48Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Sub task 2 */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [http://140.109.22.101/MediaWiki/index.php?title=Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. (TBC)&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time boundaries as follow: average start time boundary and average end time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
Set list contains &amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt; songs&lt;br /&gt;
&lt;br /&gt;
''' Ground truth: '''&lt;br /&gt;
&lt;br /&gt;
* Start time of song i：&amp;lt;math&amp;gt;sBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song i：&amp;lt;math&amp;gt;eBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
''' Identification result: ''' &lt;br /&gt;
&lt;br /&gt;
* Start time of song i：&amp;lt;math&amp;gt;sBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
* End time of song i：&amp;lt;math&amp;gt;eBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGsBD =\frac{\sum_{i=1}^N |sBD_{GT_i} - sBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGeBD =\frac{\sum_{i=1}^N |eBD_{GT_i} - eBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11040</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11040"/>
		<updated>2015-07-14T08:51:52Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Sub task 2 */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [http://140.109.22.101/MediaWiki/index.php?title=Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. (TBC)&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time boundaries as follow: average start time boundary and average end time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
Set list contains &amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt; songs&lt;br /&gt;
&lt;br /&gt;
''' Ground truth: '''&lt;br /&gt;
&lt;br /&gt;
Start time of song i：&amp;lt;math&amp;gt;sBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of song i：&amp;lt;math&amp;gt;eBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
''' Identification result: ''' &lt;br /&gt;
&lt;br /&gt;
Start time of song i：&amp;lt;math&amp;gt;sBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of song i：&amp;lt;math&amp;gt;eBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGsBD =\frac{\sum_{i=1}^N |sBD_{GT_i} - sBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGeBD =\frac{\sum_{i=1}^N |eBD_{GT_i} - eBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11039</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11039"/>
		<updated>2015-07-14T08:50:43Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Sub task 2 */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [http://140.109.22.101/MediaWiki/index.php?title=Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. (TBC)&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time boundaries as follow: average start time boundary and average end time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
Set list contains &amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt; songs&lt;br /&gt;
&lt;br /&gt;
Ground truth:&lt;br /&gt;
&lt;br /&gt;
Start time of song i：&amp;lt;math&amp;gt;sBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of song i：&amp;lt;math&amp;gt;eBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Identification result:&lt;br /&gt;
&lt;br /&gt;
Start time of song i：&amp;lt;math&amp;gt;sBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of song i：&amp;lt;math&amp;gt;eBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGsBD =\frac{\sum_{i=1}^N |sBD_{GT_i} - sBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGeBD =\frac{\sum_{i=1}^N |eBD_{GT_i} - eBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11038</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11038"/>
		<updated>2015-07-14T08:48:58Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Sub task 2 */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [http://140.109.22.101/MediaWiki/index.php?title=Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. (TBC)&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time boundaries as follow: average start time boundary and average end time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
Set list contains &amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt; songs&lt;br /&gt;
&lt;br /&gt;
Start time of ground truth song i：&amp;lt;math&amp;gt;sBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of ground truth song i：&amp;lt;math&amp;gt;eBD_{GT_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Start time of identification result song i：&amp;lt;math&amp;gt;sBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of identification result song i：&amp;lt;math&amp;gt;eBD_{ID_i}&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGsBD =\frac{\sum_{i=1}^N |sBD_{GT_i} - sBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;math&amp;gt; AVGeBD =\frac{\sum_{i=1}^N |eBD_{GT_i} - eBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11037</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11037"/>
		<updated>2015-07-14T08:48:04Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Sub task 2 */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [http://140.109.22.101/MediaWiki/index.php?title=Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. (TBC)&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time boundaries as follow: average start time boundary and average end time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
Set list contains &amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt; songs&lt;br /&gt;
&lt;br /&gt;
Start time of ground truth song i：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{GT_i}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of ground truth song i：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{GT_i}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Start time of identification result song i：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{ID_i}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of identification result song i：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{ID_i}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGsBD =\frac{\sum_{i=1}^N |sBD_{GT_i} - sBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGeBD =\frac{\sum_{i=1}^N |eBD_{GT_i} - eBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11036</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11036"/>
		<updated>2015-07-14T08:47:37Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Sub task 2 */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [http://140.109.22.101/MediaWiki/index.php?title=Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. (TBC)&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time boundaries as follow: average start time boundary and average end time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
Set list contains &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt; songs&lt;br /&gt;
&lt;br /&gt;
Start time of ground truth song i：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{GT_i}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of ground truth song i：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{GT_i}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Start time of identification result song i：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{ID_i}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of identification result song i：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{ID_i}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGsBD =\frac{\sum_{i=1}^N |sBD_{GT_i} - sBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGeBD =\frac{\sum_{i=1}^N |eBD_{GT_i} - eBD_{ID_i}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11035</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11035"/>
		<updated>2015-07-14T08:37:44Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Sub task 2 */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [http://140.109.22.101/MediaWiki/index.php?title=Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. (TBC)&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time boundaries as follow: average start time boundary and average end time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
Set list contains &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt; songs&lt;br /&gt;
&lt;br /&gt;
Start time of ground truth：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{GT}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of ground truth：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{GT}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Start time of identification result：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{ID}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of identification result：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{ID}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGsBD = \frac{|sBD_{GT} - sBD_{ID}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGeBD = \frac{|eBD_{GT} - eBD_{ID}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11020</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11020"/>
		<updated>2015-07-13T03:56:28Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Development set */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [http://140.109.22.101/MediaWiki/index.php?title=Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. (TBC)&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time time boundaries as follow: average start time boundary and average start time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
Set list contains &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt; songs&lt;br /&gt;
&lt;br /&gt;
Start time of ground truth：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{GT}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of ground truth：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{GT}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Start time of identification result：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{ID}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of identification result：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{ID}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGsBD = \frac{|sBD_{GT} - sBD_{ID}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGeBD = \frac{|eBD_{GT} - eBD_{ID}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11019</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=11019"/>
		<updated>2015-07-13T03:56:04Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Developing set */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [http://140.109.22.101/MediaWiki/index.php?title=Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Development set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. (TBC)&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time time boundaries as follow: average start time boundary and average start time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
Set list contains &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt; songs&lt;br /&gt;
&lt;br /&gt;
Start time of ground truth：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{GT}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of ground truth：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{GT}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Start time of identification result：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{ID}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of identification result：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{ID}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGsBD = \frac{|sBD_{GT} - sBD_{ID}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGeBD = \frac{|eBD_{GT} - eBD_{ID}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Main_Page&amp;diff=10995</id>
		<title>2015:Main Page</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Main_Page&amp;diff=10995"/>
		<updated>2015-07-02T08:14:35Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* MIREX 2015 Possible Evaluation Tasks */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;==Welcome to MIREX 2015==&lt;br /&gt;
&lt;br /&gt;
This is the main page for the eleventh running of the Music Information Retrieval Evaluation eXchange (MIREX 2015). The International Music Information Retrieval Systems Evaluation Laboratory ([https://music-ir.org/evaluation IMIRSEL]) at the Graduate School of Library and Information Science ([http://www.lis.illinois.edu GSLIS]), University of Illinois at Urbana-Champaign ([http://www.illinois.edu UIUC]) is the principal organizer of MIREX 2015. &lt;br /&gt;
&lt;br /&gt;
The MIREX 2015 community will hold its annual meeting as part of [http://ismir2015.uma.es The 16th International Conference on Music Information Retrieval], ISMIR 2015, which will be held in Malaga, Spain, October 26th-30th, 2015. The MIREX plenary and poster sessions will be held during the conference.&lt;br /&gt;
&lt;br /&gt;
J. Stephen Downie&amp;lt;br&amp;gt;&lt;br /&gt;
Director, IMIRSEL&amp;lt;br&amp;gt;&lt;br /&gt;
&lt;br /&gt;
==Task Leadership Model==&lt;br /&gt;
&lt;br /&gt;
Like ISMIR 2014, we are prepared to improve the distribution of tasks for the upcoming MIREX 2015.  To do so, we really need leaders to help us organize and run each task.&lt;br /&gt;
&lt;br /&gt;
To volunteer to lead a task, please add your name to the &amp;quot;Captains&amp;quot; column on the new [[2015:Task Captains]] page. Please direct any communication to the [https://mail.lis.illinois.edu/mailman/listinfo/evalfest EvalFest] mailing list.&lt;br /&gt;
&lt;br /&gt;
What does it mean to lead a task?&lt;br /&gt;
* Update wiki pages as needed&lt;br /&gt;
* Communicate with submitters and troubleshooting submissions&lt;br /&gt;
* Execution and evaluation of submissions&lt;br /&gt;
* Publishing final results&lt;br /&gt;
&lt;br /&gt;
Due to the proprietary nature of much of the data, the submission system, evaluation framework, and most of the datasets will continue to be hosted by IMIRSEL. However, we are prepared to provide access to task organizers to manage and run submissions on the IMIRSEL systems.&lt;br /&gt;
&lt;br /&gt;
We really need leaders to help us this year!&lt;br /&gt;
&lt;br /&gt;
==MIREX 2015 Deadline Dates (Tentative)==&lt;br /&gt;
&lt;br /&gt;
* '''July 16th 2015'''&lt;br /&gt;
** Audio Classification (Train/Test) Tasks &lt;br /&gt;
&lt;br /&gt;
* '''August 16th 2015'''&lt;br /&gt;
** Audio Music Similarity and Retrieval&lt;br /&gt;
** Symbolic Melodic Similarity&lt;br /&gt;
** Structural Segmentation &lt;br /&gt;
** Multiple Fundamental Frequency Estimation &amp;amp; Tracking &lt;br /&gt;
** Audio Tempo Estimation &lt;br /&gt;
** Audio Offset Detection &lt;br /&gt;
** Audio Tag Classification &lt;br /&gt;
** Set List Identification &lt;br /&gt;
** Music/Speech Classification/Detection&lt;br /&gt;
&lt;br /&gt;
* '''September 9th 2015'''&lt;br /&gt;
** Audio Onset Detection &lt;br /&gt;
** Audio Beat Tracking &lt;br /&gt;
** Audio Key Detection &lt;br /&gt;
** Audio Downbeat Detection &lt;br /&gt;
** Real-time Audio to Score Alignment(a.k.a Score Following) &lt;br /&gt;
** Audio Cover Song Identification&lt;br /&gt;
** Discovery of Repeated Themes &amp;amp; Sections&lt;br /&gt;
** Audio Melody Extraction&lt;br /&gt;
** Query by Singing/Humming&lt;br /&gt;
** Audio Chord Estimation&lt;br /&gt;
** Singing Voice Separation&lt;br /&gt;
** Audio Fingerprinting&lt;br /&gt;
&lt;br /&gt;
'''Nota Bene''': We will have about three grand UX challenges. The deadlines will be announced soon.&lt;br /&gt;
&lt;br /&gt;
==MIREX 2015 Submission Instructions==&lt;br /&gt;
* Be sure to read through the rest of this page&lt;br /&gt;
* Be sure to read though the task pages for which you are submitting&lt;br /&gt;
* Be sure to follow the [[2009:Best Coding Practices for MIREX | Best Coding Practices for MIREX]]&lt;br /&gt;
* Be sure to follow the  [[MIREX 2014 Submission Instructions]] including both the tutorial video and the text&lt;br /&gt;
&lt;br /&gt;
==MIREX 2015 Possible Evaluation Tasks==&lt;br /&gt;
&lt;br /&gt;
* [[2015:GC15UX|2015:Grand Challenge on User Experience]]&lt;br /&gt;
* [[2015:Audio Classification (Train/Test) Tasks]], incorporating:&lt;br /&gt;
** Audio US Pop Genre Classification&lt;br /&gt;
** Audio Latin Genre Classification&lt;br /&gt;
** Audio Music Mood Classification&lt;br /&gt;
** Audio Classical Composer Identification&lt;br /&gt;
** [[2015:Audio K-POP Mood Classification]]&lt;br /&gt;
** [[2015:Audio K-POP Genre Classification]]&lt;br /&gt;
* [[2015:Audio Cover Song Identification]]&lt;br /&gt;
* [[2015:Audio Tag Classification]] &lt;br /&gt;
* [[2015:Audio Music Similarity and Retrieval]]&lt;br /&gt;
* [[2015:Symbolic Melodic Similarity]]&lt;br /&gt;
* [[2015:Audio Onset Detection]]&lt;br /&gt;
* [[2015:Audio Key Detection]]&lt;br /&gt;
* [[2015:Real-time Audio to Score Alignment (a.k.a Score Following)]]&lt;br /&gt;
* [[2015:Query by Singing/Humming]]&lt;br /&gt;
* [[2015:Audio Melody Extraction]]&lt;br /&gt;
* [[2015:Multiple Fundamental Frequency Estimation &amp;amp; Tracking]]&lt;br /&gt;
* [[2015:Audio Chord Estimation]]&lt;br /&gt;
* [[2015:Query by Tapping]]&lt;br /&gt;
* [[2015:Audio Beat Tracking]]&lt;br /&gt;
* [[2015:Structural Segmentation]]&lt;br /&gt;
* [[2015:Audio Tempo Estimation]]&lt;br /&gt;
* [[2015:Discovery of Repeated Themes &amp;amp; Sections]]&lt;br /&gt;
* [[2015:Audio Downbeat Estimation]]&lt;br /&gt;
* [[2015:Audio Fingerprinting]]&lt;br /&gt;
* [[2015:Singing Voice Separation]]&lt;br /&gt;
* [[2015:Set List Identification]]&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Note to New Participants===&lt;br /&gt;
Please take the time to read the following review articles that explain the history and structure of MIREX.&lt;br /&gt;
&lt;br /&gt;
Downie, J. Stephen (2008). The Music Information Retrieval Evaluation Exchange (2005-2007):&amp;lt;br&amp;gt;&lt;br /&gt;
A window into music information retrieval research.''Acoustical Science and Technology 29'' (4): 247-255. &amp;lt;br&amp;gt;&lt;br /&gt;
Available at: [http://dx.doi.org/10.1250/ast.29.247 http://dx.doi.org/10.1250/ast.29.247]&lt;br /&gt;
&lt;br /&gt;
Downie, J. Stephen, Andreas F. Ehmann, Mert Bay and M. Cameron Jones. (2010).&amp;lt;br&amp;gt;&lt;br /&gt;
The Music Information Retrieval Evaluation eXchange: Some Observations and Insights.&amp;lt;br&amp;gt;&lt;br /&gt;
''Advances in Music Information Retrieval'' Vol. 274, pp. 93-115&amp;lt;br&amp;gt;&lt;br /&gt;
Available at: [http://bit.ly/KpM5u5 http://bit.ly/KpM5u5]&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Runtime Limits===&lt;br /&gt;
&lt;br /&gt;
We reserve the right to stop any process that exceeds runtime limits for each task.  We will do our best to notify you in enough time to allow revisions, but this may not be possible in some cases. Please respect the published runtime limits.&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Note to All Participants===&lt;br /&gt;
&lt;br /&gt;
Because MIREX is premised upon the sharing of ideas and results, '''ALL''' MIREX participants are expected to:&lt;br /&gt;
&lt;br /&gt;
# submit a DRAFT 2-3 page extended abstract PDF in the ISMIR format about the submitted programme(s) to help us and the community better understand how the algorithm works when submitting their programme(s).&lt;br /&gt;
# submit a FINALIZED 2-3 page extended abstract PDF in the ISMIR format prior to ISMIR 2014 for posting on the respective results pages (sometimes the same abstract can be used for multiple submissions; in many cases the DRAFT and FINALIZED abstracts are the same)&lt;br /&gt;
# present a poster at the MIREX 2014 poster session at ISMIR 2014&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Software Dependency Requests===&lt;br /&gt;
If you have not submitted to MIREX before or are unsure whether IMIRSEL currently supports some of the software/architecture dependencies for your submission a [https://docs.google.com/forms/d/1ZgC72BhhN0PFFiaj9NDejRdl1eW7wAFLIyMhAtoV0CA/viewform?usp=send_form dependency request form is available]. Please submit details of your dependencies on this form and the IMIRSEL team will attempt to satisfy them for you. &lt;br /&gt;
&lt;br /&gt;
Due to the high volume of submissions expected at MIREX 2015, submissions with difficult to satisfy dependencies that the team has not been given sufficient notice of may result in the submission being rejected.&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
Finally, you will also be expected to detail your software/architecture dependencies in a README file to be provided to the submission system.&lt;br /&gt;
&lt;br /&gt;
==Getting Involved in MIREX 2015==&lt;br /&gt;
MIREX is a community-based endeavour. Be a part of the community and help make MIREX 2015 the best yet.&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Mailing List Participation===&lt;br /&gt;
If you are interested in formal MIR evaluation, you should also subscribe to the &amp;quot;MIREX&amp;quot; (aka &amp;quot;EvalFest&amp;quot;) mail list and participate in the community discussions about defining and running MIREX 2015 tasks. Subscription information at: &lt;br /&gt;
[https://mail.lis.illinois.edu/mailman/listinfo/evalfest EvalFest Central]. &lt;br /&gt;
&lt;br /&gt;
If you are participating in MIREX 2015, it is VERY IMPORTANT that you are subscribed to EvalFest. Deadlines, task updates and other important information will be announced via this mailing list. Please use the EvalFest for discussion of MIREX task proposals and other MIREX related issues. This wiki (MIREX 2015 wiki) will be used to embody and disseminate task proposals, however, task related discussions should be conducted on the MIREX organization mailing list (EvalFest) rather than on this wiki, but should be summarized here. &lt;br /&gt;
&lt;br /&gt;
Where possible, definitions or example code for new evaluation metrics or tasks should be provided to the IMIRSEL team who will embody them in software as part of the NEMA analytics framework, which will be released to the community at or before ISMIR 2015 - providing a standardised set of interfaces and output to disciplined evaluation procedures for a great many MIR tasks.&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
===Wiki Participation===&lt;br /&gt;
If you find that you cannot edit a MIREX wiki page, you will need to create a new account via: [[Special:Userlogin]].&lt;br /&gt;
&lt;br /&gt;
Please note that because of &amp;quot;spam-bots&amp;quot;, MIREX wiki registration requests may be moderated by IMIRSEL members. It might take up to 24 hours for approval (Thank you for your patience!).&lt;br /&gt;
&lt;br /&gt;
==MIREX 2005 - 2014 Wikis==&lt;br /&gt;
Content from MIREX 2005 - 2014 are available at:&lt;br /&gt;
'''[[2014:Main_Page|MIREX 2013]]''' &lt;br /&gt;
'''[[2013:Main_Page|MIREX 2013]]''' &lt;br /&gt;
'''[[2012:Main_Page|MIREX 2012]]''' &lt;br /&gt;
'''[[2011:Main_Page|MIREX 2011]]''' &lt;br /&gt;
'''[[2010:Main_Page|MIREX 2010]]''' &lt;br /&gt;
'''[[2009:Main_Page|MIREX 2009]]''' &lt;br /&gt;
'''[[2008:Main_Page|MIREX 2008]]''' &lt;br /&gt;
'''[[2007:Main_Page|MIREX 2007]]''' &lt;br /&gt;
'''[[2006:Main_Page|MIREX 2006]]''' &lt;br /&gt;
'''[[2005:Main_Page|MIREX 2005]]'''&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=10992</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=10992"/>
		<updated>2015-06-18T09:48:26Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Data */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [http://140.109.22.101/MediaWiki/index.php?title=Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We extract features for the convenience of participants, the links is the tool we used. (TBC)&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time time boundaries as follow: average start time boundary and average start time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
Set list contains &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt; songs&lt;br /&gt;
&lt;br /&gt;
Start time of ground truth：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{GT}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of ground truth：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{GT}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Start time of identification result：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{ID}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of identification result：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{ID}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGsBD = \frac{|sBD_{GT} - sBD_{ID}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGeBD = \frac{|eBD_{GT} - eBD_{ID}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=10991</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=10991"/>
		<updated>2015-06-18T09:46:08Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Data */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [http://140.109.22.101/MediaWiki/index.php?title=Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We also prepare feature for participants, the links is the tool we used. (TBC)&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time time boundaries as follow: average start time boundary and average start time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
Set list contains &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt; songs&lt;br /&gt;
&lt;br /&gt;
Start time of ground truth：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{GT}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of ground truth：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{GT}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Start time of identification result：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{ID}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of identification result：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{ID}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGsBD = \frac{|sBD_{GT} - sBD_{ID}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGeBD = \frac{|eBD_{GT} - eBD_{ID}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=10990</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=10990"/>
		<updated>2015-06-18T08:48:03Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Developing set */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [http://140.109.22.101/MediaWiki/index.php?title=Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0 Dropbox])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We also prepare feature for participants, the links is the tool we used.&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time time boundaries as follow: average start time boundary and average start time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
Set list contains &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt; songs&lt;br /&gt;
&lt;br /&gt;
Start time of ground truth：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{GT}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of ground truth：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{GT}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Start time of identification result：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{ID}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of identification result：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{ID}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGsBD = \frac{|sBD_{GT} - sBD_{ID}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGeBD = \frac{|eBD_{GT} - eBD_{ID}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=10989</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=10989"/>
		<updated>2015-06-18T08:47:48Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Developing set */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [http://140.109.22.101/MediaWiki/index.php?title=Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release ([Dropbox https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We also prepare feature for participants, the links is the tool we used.&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time time boundaries as follow: average start time boundary and average start time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
Set list contains &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt; songs&lt;br /&gt;
&lt;br /&gt;
Start time of ground truth：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{GT}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of ground truth：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{GT}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Start time of identification result：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{ID}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of identification result：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{ID}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGsBD = \frac{|sBD_{GT} - sBD_{ID}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGeBD = \frac{|eBD_{GT} - eBD_{ID}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=10988</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=10988"/>
		<updated>2015-06-18T08:47:24Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Developing set */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [http://140.109.22.101/MediaWiki/index.php?title=Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release (Dropbox [https://www.dropbox.com/sh/t83ogdrxi0f050n/AABb11MCcQUokqSjOsqhArOFa?dl=0])&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We also prepare feature for participants, the links is the tool we used.&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time time boundaries as follow: average start time boundary and average start time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
Set list contains &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt; songs&lt;br /&gt;
&lt;br /&gt;
Start time of ground truth：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{GT}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of ground truth：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{GT}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Start time of identification result：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{ID}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of identification result：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{ID}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGsBD = \frac{|sBD_{GT} - sBD_{ID}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGeBD = \frac{|eBD_{GT} - eBD_{ID}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
	<entry>
		<id>https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=10987</id>
		<title>2015:Set List Identification</title>
		<link rel="alternate" type="text/html" href="https://music-ir.org/mirex/w/index.php?title=2015:Set_List_Identification&amp;diff=10987"/>
		<updated>2015-06-16T11:56:42Z</updated>

		<summary type="html">&lt;p&gt;Ming-Chi Yen: /* Data */&lt;/p&gt;
&lt;hr /&gt;
&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
==Description==&lt;br /&gt;
&lt;br /&gt;
'''This task is new for 2015!'''&lt;br /&gt;
&lt;br /&gt;
This task requires that algorithm identify the '''set list''' (See [http://en.wikipedia.org/wiki/Set_list Set list]). Set list is the song sequence in a live concert. It shows the order of songs will be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
Recently, more and more full-length live concert videos have become available on website (e.g. [https://www.youtube.com/ Youtube]). Most of them are lacking sufficient information to describe itself, such as the set list, and start/end time of each song. In this task, we collect the audio of live concerts and studio songs, applying music information retrieval techniques to answer this question -- what songs had been sung in this concert and when are the songs start and end.&lt;br /&gt;
&lt;br /&gt;
For the first step of this task, we assume that '''artist is known'''. In the live concert, '''the performers play their studio songs only''', however the ultimate goal is granted a full-length live concert audio and studio song database, we still can find out the set list and the start/end time of each song.&lt;br /&gt;
&lt;br /&gt;
here are two sub tasks in this task:&lt;br /&gt;
&lt;br /&gt;
===Sub task 1: Song sequence identification===&lt;br /&gt;
*To identify the order of songs which be performed in a live concert.&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the the artist and artist's studio song collection. Assigning a live concert audio and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify the order of songs in this live concert.&lt;br /&gt;
&lt;br /&gt;
===Sub task 2: Time boundary identification===&lt;br /&gt;
*To identify the start/end time of each song in song sequence&lt;br /&gt;
&lt;br /&gt;
In this sub task, the participants known the artist, artist's studio song collection and the '''song sequence'''. Assigning a live concert audio, song sequence and studio songs collection of a specific artist, all songs in live concert are included in studio songs collection, to identify start time and end time of each song in the live concert.&lt;br /&gt;
&lt;br /&gt;
== Data ==&lt;br /&gt;
To satisfy our assessment, we pre-process all audio -- '''remove the &amp;quot;out of artist song&amp;quot; form live concert audio''' for following our assumption. (See the [http://140.109.22.101/MediaWiki/index.php?title=Set_List_Identification#Description description])&lt;br /&gt;
&lt;br /&gt;
We provide two set for this task,participating algorithms will have to read audio in the following format.&lt;br /&gt;
&lt;br /&gt;
* Sample rate: 22050 Hz&lt;br /&gt;
* Sample size: 16 bit&lt;br /&gt;
* Number of channels: 1 (mono)&lt;br /&gt;
* Encoding: WAV &lt;br /&gt;
&lt;br /&gt;
===Developing set===&lt;br /&gt;
This set contain 3 artists and 7 live concerts, the following information would be release:&lt;br /&gt;
* artist&lt;br /&gt;
* live concert name and links&lt;br /&gt;
* studio collection list&lt;br /&gt;
* start/end time tags&lt;br /&gt;
&lt;br /&gt;
We also prepare feature for participants, the links is the tool we used.&lt;br /&gt;
*chroma (CRP features [http://resources.mpi-inf.mpg.de/MIR/chromatoolbox/ Chroma Toolbox])&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 3 artists&lt;br /&gt;
* 7 live concerts&lt;br /&gt;
* 279 tracks&lt;br /&gt;
&lt;br /&gt;
=== Testing set ===&lt;br /&gt;
This set contain 7 artists and 13 live concerts, no information would be release.&lt;br /&gt;
&lt;br /&gt;
Collection statistics:&lt;br /&gt;
* 7 artists&lt;br /&gt;
* 13 live concerts&lt;br /&gt;
* 873 tracks&lt;br /&gt;
&lt;br /&gt;
== Evaluation ==&lt;br /&gt;
&lt;br /&gt;
For two tasks, the evaluation metrics were different.&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1===&lt;br /&gt;
&lt;br /&gt;
* Edit distance (see [http://en.wikipedia.org/wiki/Edit_distance Edit distance])&lt;br /&gt;
 &lt;br /&gt;
We evaluated the two sequence (ground truth and your result) by edit distance, there three errors included&lt;br /&gt;
* insertion error &amp;lt;math&amp;gt;I&amp;lt;/math&amp;gt;&lt;br /&gt;
* substitution error &amp;lt;math&amp;gt;S&amp;lt;/math&amp;gt;&lt;br /&gt;
* deletion error &amp;lt;math&amp;gt;D&amp;lt;/math&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Edit Distance: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;ED = I+S+D &amp;lt;/math&amp;gt; &amp;lt;/big&amp;gt; &lt;br /&gt;
&lt;br /&gt;
Percent Correct: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;Corr = \frac{N-D-S}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Percent Accuracy: &amp;lt;big&amp;gt;&amp;lt;math&amp;gt; Acc = \frac{N-D-S-I}{N}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2===&lt;br /&gt;
&lt;br /&gt;
* average time boundary&lt;br /&gt;
&lt;br /&gt;
We will evaluate two time time boundaries as follow: average start time boundary and average start time boundary. The evaluation function is described below:&lt;br /&gt;
&lt;br /&gt;
Set list contains &amp;lt;big&amp;gt;&amp;lt;math&amp;gt;N&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt; songs&lt;br /&gt;
&lt;br /&gt;
Start time of ground truth：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{GT}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of ground truth：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{GT}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Start time of identification result：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;sBD_{ID}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
End time of identification result：&amp;lt;big&amp;gt;&amp;lt;math&amp;gt;eBD_{ID}&amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGsBD = \frac{|sBD_{GT} - sBD_{ID}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
&amp;lt;big&amp;gt;&amp;lt;math&amp;gt; AVGeBD = \frac{|eBD_{GT} - eBD_{ID}|}{N}  &amp;lt;/math&amp;gt;&amp;lt;/big&amp;gt;,&lt;br /&gt;
&lt;br /&gt;
=== Runtime performance ===&lt;br /&gt;
In addition computation times for feature extraction and training/classification will be measured.&lt;br /&gt;
&lt;br /&gt;
== Submission Format ==&lt;br /&gt;
* '''\n''' is end of line&lt;br /&gt;
&lt;br /&gt;
Submission to this task will have to conform to a specified format detailed below.&lt;br /&gt;
=== Implementation details ===&lt;br /&gt;
we recommend your submission folder construction as follow:&lt;br /&gt;
 /root_folder/... all the code you submitted&lt;br /&gt;
 /root_folder/extract_feature/... all feature your extracted&lt;br /&gt;
 /root_folder/output/... the folder to save results&lt;br /&gt;
&lt;br /&gt;
=== Sub task 1 ===&lt;br /&gt;
&lt;br /&gt;
==== Input file ====&lt;br /&gt;
The input for studio songs list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/studio/song/001.wav\n  1st&lt;br /&gt;
 /path/to/artist_1/studio/song/002.wav\n  2nd&lt;br /&gt;
 /path/to/artist_1/studio/song/003.wav\n  3rd&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
The input for live concert list file format will be of the form:&lt;br /&gt;
&lt;br /&gt;
 /path/to/artist_1/live/concert/001.wav\n&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
The output is a list file (song ID sequence), '''the song ID is the order of input list file''', not the file name of *.wav file.&lt;br /&gt;
&lt;br /&gt;
 3\n   &amp;lt;-- 003.wav is the first song of set list for your identification result&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Sub task 2 ===&lt;br /&gt;
==== Input file ====&lt;br /&gt;
&lt;br /&gt;
The input is a list of song ID (song ID sequence), '''the song ID is the order of studio songs list file'''.&lt;br /&gt;
&lt;br /&gt;
Your system should read the *.wav file according that order and find the time boundary of the song.&lt;br /&gt;
&lt;br /&gt;
 3\n&lt;br /&gt;
 17\n&lt;br /&gt;
 59\n&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
==== Output file ====&lt;br /&gt;
&lt;br /&gt;
The output for studio songs time boundary list file format will be of the form:&lt;br /&gt;
* please round the time boundary to millisecond&lt;br /&gt;
* '''\t''' is tab space&lt;br /&gt;
 Start time                           end time&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:3&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:17&lt;br /&gt;
 hours.minutes.seconds.milliseconds \t hours.minutes.seconds.milliseconds\n  ...for input input sond ID:59&lt;br /&gt;
 ... &lt;br /&gt;
&lt;br /&gt;
Examples:&lt;br /&gt;
 0.7.23.521    0.13.24.512&lt;br /&gt;
 0.14.3.021    0.19.53.38&lt;br /&gt;
 0.20.9.893    0.27.15.987&lt;br /&gt;
 ...&lt;br /&gt;
 ...&lt;br /&gt;
 0.56.22.433    1.1.46.593&lt;br /&gt;
 1.3.51.146    1.9.21.138&lt;br /&gt;
 ...&lt;br /&gt;
&lt;br /&gt;
=== Packaging submissions ===&lt;br /&gt;
&lt;br /&gt;
All submissions should be statically linked to all libraries (the presence of dynamically linked libraries cannot be guarenteed).&lt;br /&gt;
&lt;br /&gt;
All submissions should include a README file including the following the information:&lt;br /&gt;
&lt;br /&gt;
* Which task you want to participate (sub task1, sub task2 or all)&lt;br /&gt;
* Command line calling format for all executables and an example formatted set of commands&lt;br /&gt;
* Number of threads/cores used or whether this should be specified on the command line&lt;br /&gt;
* Expected memory footprint&lt;br /&gt;
* Expected runtime&lt;br /&gt;
* Any required environments (and versions), e.g. python, java, bash, matlab.&lt;br /&gt;
&lt;br /&gt;
== Time and hardware limits ==&lt;br /&gt;
Due to the potentially high number of particpants in this and other audio tasks, hard limits on the runtime of submissions are specified. &lt;br /&gt;
 &lt;br /&gt;
A hard limit of 72 hours will be imposed on runs (total feature extraction and querying times). Submissions that exceed this runtime may not receive a result.&lt;br /&gt;
&lt;br /&gt;
== Potential Participants ==&lt;br /&gt;
name / email&lt;/div&gt;</summary>
		<author><name>Ming-Chi Yen</name></author>
		
	</entry>
</feed>