2007:Discussion Points Euro MIREX Meeting - Revision history

Kahyun Choi: /* Topic 13: Relationships between features */

2011-12-15T06:47:13Z

‎Topic 13: Relationships between features

Kahyun Choi: /* Topic 4: New task of structural analysis */

2011-12-15T06:46:55Z

‎Topic 4: New task of structural analysis

Kahyun Choi: /* Topic 2: First Proposal on Audio Music Mood Classification */

2011-12-15T06:46:37Z

‎Topic 2: First Proposal on Audio Music Mood Classification

Kahyun Choi: /* Topic 1: First Task Proposal For MIREXDIYDEMO Prototype: Audio Cover Song? */

2011-12-15T06:46:23Z

‎Topic 1: First Task Proposal For MIREXDIYDEMO Prototype: Audio Cover Song?

Paulus: /* Topic 13: Braining-storming full task list and potential contact points/moderators */

2007-04-23T10:29:34Z

‎Topic 13: Braining-storming full task list and potential contact points/moderators

Paulus: /* Topic 13: Braining-storming full task list and potential contact points/moderators */

2007-04-23T10:02:06Z

‎Topic 13: Braining-storming full task list and potential contact points/moderators

Hamish: /* Topic 13: Relationships between features */

2007-04-23T09:59:47Z

‎Topic 13: Relationships between features

Paulus: /* Topic 4: New task of structural analysis */

2007-04-23T09:56:34Z

‎Topic 4: New task of structural analysis

Paulus: /* Topic 3: Resurrecting drum detection task from 2005 */

2007-04-23T09:50:35Z

‎Topic 3: Resurrecting drum detection task from 2005

Hamish at 09:47, 23 April 2007

2007-04-23T09:47:39Z

@@ Line 227: / Line 227: @@
 * Do we want to use an ontology to describe features so that they can be equated?
 * How should data be passed around?
-* Personally, from an M2K point of view, I would like to see intelligent caching. My concept of a feature is related to what is upstream of it. So if I ask for the GMMs of MFCCs of Magical Mystery Tour (with a particular parameter set), they might already have been calculated and cached; if not, the system knows to look for the MFCCs of MMT, if they haven't been calculated the system needs to get MMT, etc. This has the advantage that a policy might be set for certain features that they can be made public -- e.g. MFCCs and phaseless STFT might be okay, full STFT might not be, but onsets determined from full STFT might be. [[User:Hamish|Hamish]] 04:59, 23 April 2007 (CDT)
+* Personally, from an M2K point of view, I would like to see intelligent caching. My concept of a feature is related to what is upstream of it. So if I ask for the GMMs of MFCCs of Magical Mystery Tour (with a particular parameter set), they might already have been calculated and cached; if not, the system knows to look for the MFCCs of MMT, if they haven't been calculated the system needs to get MMT, etc. This has the advantage that a policy might be set for certain features that they can be made public -- e.g. MFCCs and phaseless STFT might be okay, full STFT might not be, but onsets determined from full STFT might be. Hamish 04:59, 23 April 2007 (CDT)

@@ Line 53: / Line 53: @@
 * Start planning and collecting data now, but run in 2008?
---[[User:Paulus|Paulus]] 09:02, 20 April 2007 (CDT)
+-- Paulus 09:02, 20 April 2007 (CDT)
 ===Topic 5: (Audio) Rhythmic similarity===

← Older revision		Revision as of 06:46, 15 December 2011
Line 25:		Line 25:


−	--~~[[User:~~Claurier~~\|Claurier]]~~ 06:53, 19 April 2007 (CDT)	+	-- Claurier 06:53, 19 April 2007 (CDT)

	===Topic 3: Resurrecting drum detection task from 2005===		===Topic 3: Resurrecting drum detection task from 2005===

@@ Line 7: / Line 7: @@
 I would appreciate comments and feedback on the idea that we re-run the Audio Cover Song task with the option (encouragement?) that participants use the the proposed MIREXDIYDEMO framework for submission and evaluation. I believe that Audio Cover Song is a good choice because the the ground-truth is fixed (i.e., either the returned items are cover songs or not) and thus requires no human intervention. Open to other suggestions along the same lines. Does look now (as of 11 April, 2007) that we will only be able to support MATLAB and JAVA submissions but this might be subject to change. Fool around with the preliminary prototype at http://cluster3.lis.uiuc.edu:8080/mirexdiydemo/. By the time we reach Vienna, we hope have a Version II up but this, unfortunately (for security reasons), will probably '''not''' be open to the general community.
-[[User:JDownie|JDownie]] 10:50, 12 April 2007 (CDT)
+JDownie 10:50, 12 April 2007 (CDT)
 ===Topic 2: First Proposal on Audio Music Mood Classification===

← Older revision		Revision as of 10:29, 23 April 2007
Line 99:		Line 99:

	* Polyphonic transcription/ Multi F0 estimation		* Polyphonic transcription/ Multi F0 estimation
−	** Josh Reiss & Geoffrey Peters (others on wiki - Mert Bay, Chungsin yeh)	+	** Josh Reiss & Geoffrey Peters (others on wiki - Mert Bay, Chungsin yeh), Matti Ryyn├ñnen

@@ Line 116: / Line 116: @@
 ** Kris West, (Hamish?), (Elias?), (Fabien G.?), Ben Fields, Thomas Lidy
 ** Query by tapping (etc.)
-*** Rainer - Cory McKay
+*** Rainer - Cory McKay, Paulus
 *** Note ROger Jang's sunbg query DB
@@ Line 167: / Line 167: @@
 * Audio Chord detection
-** Katja Rosenbauer (Fraunhofer IDMT, Ilmenau, Germany), Christian Dittmar (Fraunhofer IDMT, Ilmenau, Germany), (Ben Fields?) (Chris Hart's method)
+** Katja Rosenbauer (Fraunhofer IDMT, Ilmenau, Germany), Christian Dittmar (Fraunhofer IDMT, Ilmenau, Germany), (Ben Fields?) (Chris Hart's method), Matti Ryyn├ñnen (TUT)
@@ Line 202: / Line 202: @@
 * Segmenting (Audio) - structure analysis/phrase boundary detection
-** Josh Reiss, Ben Fields
+** Josh Reiss, Ben Fields, Jouni Paulus
 ** Produce human annotations and get probability distribution across many evaluators
@@ Line 220: / Line 220: @@
 * Query by Singing/Humming
 ** Rainer, Roger Jang, Niko Mikkila
 ===Topic 13: Relationships between features===

← Older revision		Revision as of 09:59, 23 April 2007
Line 224:		Line 224:

	===Topic 13: Relationships between features===		===Topic 13: Relationships between features===
		+
		+	There is an interest in storing and re-using features calculated from audio, which leads to the question of how to manage the relationships between low-level and higher-level features.
		+
		+	* Do we want to use an ontology to describe features so that they can be equated?
		+	* How should data be passed around?
		+	* Personally, from an M2K point of view, I would like to see intelligent caching. My concept of a feature is related to what is upstream of it. So if I ask for the GMMs of MFCCs of Magical Mystery Tour (with a particular parameter set), they might already have been calculated and cached; if not, the system knows to look for the MFCCs of MMT, if they haven't been calculated the system needs to get MMT, etc. This has the advantage that a policy might be set for certain features that they can be made public -- e.g. MFCCs and phaseless STFT might be okay, full STFT might not be, but onsets determined from full STFT might be. [[User:Hamish\|Hamish]] 04:59, 23 April 2007 (CDT)

@@ Line 42: / Line 42: @@
 ** Chorus detection has been done more and there would be data available from RWC. Chorus detection in a way easier problem to specify and to evaluate.
 ** Full description harder. What is correct description? (Levels of hierarchy and locations of borders between parts, etc.)
-* Data
+* Data (big problem)
 ** RWC: AIST annotations of chorus sections, available for all
 ** TUT-structure data: commercial audio (also part from RWC Pop), annotations of clear repeated parts + some solos etc. Annotations do not cover whole songs. Amount of data limited, just 50 pieces. Ground truth not available publicly, but for the evaluation.
 ** Beatles data: Some annotations are known to be made based on Alan Pollock's "notes on"-series. Availability of the ground truth?
 * Participants?
 --[[User:Paulus|Paulus]] 09:02, 20 April 2007 (CDT)

@@ Line 29: / Line 29: @@
 ===Topic 3: Resurrecting drum detection task from 2005===
-The task could be run quite easily based on the decisions and specifications from 2005. But would there be enough participants? New data from ENST-drums?
+The task could be run quite easily based on the decisions and specifications from 2005:
 ===Topic 4: New task of structural analysis===

@@ Line 13: / Line 13: @@
 Main points to discuss:
-*Taxonomy
+*Taxonom
 **Derived from music perception theories : Dimensional like Thayer's or Categorical like Juslin, Hevner
 **Taken from a practical data collection (and maybe clustering to have less categories) : AllMusicGuild, MoodLogic, LastFM
@@ Line 209: / Line 209: @@
 * Query by Singing/Humming
 ** Rainer, Roger Jang, Niko Mikkila