Difference between revisions of "2018:Music and or Speech Detection Results"

From MIREX Wiki
Line 112: Line 112:
 
| 0.5177 || 0.2693 || 0.5813 || 0.3502
 
| 0.5177 || 0.2693 || 0.5813 || 0.3502
 
         |}
 
         |}
−
 
−
'''Notes on metrics:'''
 
−
 
−
Music_F = segment-level F-measure for the music class
 
−
 
−
No-Music_F = segment-level F-measure for the no-music class
 
−
 
−
Music_F_500_on = onset-only event-level F-measure (500 ms tolerance) for the music class
 
−
 
−
Music_F_500_onoff = onset-offset event-level F-measure (500 ms tolerance) for the music class
 
−
 
−
Music_F_1000_on = onset-only event-level F-measure (1000 ms tolerance) for the music class
 
−
 
−
Music_F_1000_onoff = onset-offset event-level F-measure (1000 ms tolerance) for the music class
 
  
 
==Task 2: Speech Detection==
 
==Task 2: Speech Detection==
Line 137: Line 123:
 
! width="80" | Sub code  
 
! width="80" | Sub code  
 
! width="80" style="text-align: center;" | Accuracy  
 
! width="80" style="text-align: center;" | Accuracy  
−
! width="80" | Speech F-measure
+
! width="80" | Speech_F
−
! width="80" | No-Speech F-measure
+
! width="80" | No-Speech_F
 
|-
 
|-
 
! DD1
 
! DD1
Line 187: Line 173:
 
| 0.4439 || 0.1775 || 0.4879 || 0.2122
 
| 0.4439 || 0.1775 || 0.4879 || 0.2122
 
         |}
 
         |}
−
 
−
'''Notes on metrics:'''
 
−
 
−
Speech_F = segment-level F-measure for the speech class
 
−
 
−
No-Speech_F = segment-level F-measure for the no-speech class
 
−
 
−
Speech_F_500_on = onset-only event-level F-measure (500 ms tolerance) for the speech class
 
−
 
−
Speech_F_500_onoff = onset-offset event-level F-measure (500 ms tolerance) for the speech class
 
−
 
−
Speech_F_1000_on = onset-only event-level F-measure (1000 ms tolerance) for the speech class
 
−
 
−
Speech_F_1000_onoff = onset-offset event-level F-measure (1000 ms tolerance) for the speech class
 
  
 
==Task 3: Music and Speech Detection==
 
==Task 3: Music and Speech Detection==
Line 211: Line 183:
 
|- style="background: yellow;"
 
|- style="background: yellow;"
 
! width="80" | Sub code  
 
! width="80" | Sub code  
−
! width="80" style="text-align: center;" | Music F-measure
+
! width="80" style="text-align: center;" | Music_F
−
! width="80" | Speech F-measure
+
! width="80" | Speech_F
 
|-
 
|-
 
! LN1
 
! LN1
Line 293: Line 265:
 
| 0.3298 || 0.1775 || 0.4106 || 0.2742 || 0.3853 || 0.1388 || 0.4463 || 0.2024 || 0.5254 || 0.3123 || 0.5927 || 0.3925
 
| 0.3298 || 0.1775 || 0.4106 || 0.2742 || 0.3853 || 0.1388 || 0.4463 || 0.2024 || 0.5254 || 0.3123 || 0.5927 || 0.3925
 
         |}
 
         |}
 +
 +
'''Notes on metrics:'''
 +
 +
<class>_F = segment-level F-measure for the class <class>
 +
 +
<class>_F_500_on = onset-only event-level F-measure (500 ms tolerance) for the class <class>
 +
 +
<class>_F_500_onoff = onset-offset event-level F-measure (500 ms tolerance) for the class <class>
 +
 +
<class>_F_1000_on = onset-only event-level F-measure (1000 ms tolerance) for the class <class>
 +
 +
<class>_F_1000_onoff = onset-offset event-level F-measure (1000 ms tolerance) for the class <class>

Revision as of 10:32, 17 September 2018

Introduction

These are the results for the 2018 running of the Music and/or Speech Detection tasks. For background information about this task set please refer to the 2018:Music and/or Speech Detection page.

General Legend

Sub code Abstract Contributors
DD1 PDF David Doukhan
JHKK1 PDF Byeong-Yong Jang, Woon-Haeng Heo, Jung-Hyun Kim, Oh-Wook Kwon
JHKK2 PDF Byeong-Yong Jang, Woon-Haeng Heo, Jung-Hyun Kim, Oh-Wook Kwon
JHKK3 PDF Byeong-Yong Jang, Woon-Haeng Heo, Jung-Hyun Kim, Oh-Wook Kwon
LN1 PDF Minsuk Choi, Jongpil Lee, Juhan Nam
MM1 PDF Matija Marolt
MM2 PDF Matija Marolt
MM3 PDF Matija Marolt
MMG1 PDF Blai Meléndez-Catalán, Emilio Molina, Emilia Gómez
MMG2 PDF Blai Meléndez-Catalán, Emilio Molina, Emilia Gómez

Task 1: Music Detection

Dataset 1

Segment-level Evaluation

Sub code Accuracy Music_F No-Music_F
DD1 0.6860 0.5424 0.7611
JHKK1 0.7798 0.7123 0.8215
JHKK2 0.8005 0.7415 0.8375
LN1 0.6251 0.5022 0.6987
MM1 0.6135 0.3899 0.7172
MM2 0.6807 0.5478 0.7531
MM3 0.6075 0.3124 0.7254
MMG1 0.9049 0.8996 0.9097

Event-level Evaluation

Sub code Music_F_500_on Music_F_500_onoff Music_F_1000_on Music_F_1000_onoff
DD1 0.2877 0.093 0.312 0.1142
JHKK1 0.2303 0.0765 0.294 0.1173
JHKK2 0.2522 0.0931 0.3245 0.1389
LN1 0.1348 0.0139 0.1704 0.0231
MM1 0.2044 0.0662 0.2137 0.0831
MM2 0.2464 0.0817 0.2736 0.1049
MM3 0.1379 0.0525 0.1619 0.0676
MMG1 0.5177 0.2693 0.5813 0.3502

Task 2: Speech Detection

Segment-level Evaluation

Dataset 1

Sub code Accuracy Speech_F No-Speech_F
DD1 0.877 0.9186 0.7493
JHKK3 0.8307 0.8795 0.7143
LN1 0.6908 0.7472 0.6007
MM1 0.8626 0.9115 0.6948
MM2 0.8619 0.909 0.713
MM3 0.8508 0.9086 0.5966

Event-level Evaluation

Sub code Speech_F_500_on Speech_F_500_onoff Speech_F_1000_on Speech_F_1000_onoff
DD1 0.415 0.1603 0.4477 0.2122
JHKK3 0.2882 0.0777 0.3289 0.0962
LN1 0.2686 0.0529 0.3484 0.0883
MM1 0.4607 0.2068 0.4898 0.2336
MM2 0.4422 0.1999 0.5093 0.266
MM3 0.4439 0.1775 0.4879 0.2122

Task 3: Music and Speech Detection

Segment-level Evaluation

Dataset 1

Sub code Music_F Speech_F
LN1 0.4936 0.7718
MM1 0.3899 0.9115
MM2 0.5478 0.909
MM3 0.3124 0.9086

Event-level Evaluation

Sub code Music_F_500_on Music_F_500_onoff Music_F_1000_on Music_F_1000_onoff Speech_F_500_on Speech_F_500_onoff Speech_F_1000_on Speech_F_1000_onoff
LN1 0.1116 0.0088 0.1459 0.0186 0.2645 0.0462 0.348 0.0786
MM1 0.2044 0.0662 0.2137 0.0831 0.4607 0.2068 0.4898 0.2336
MM2 0.2464 0.0817 0.2736 0.1049 0.4422 0.1999 0.5093 0.266
MM3 0.1379 0.0525 0.1619 0.0676 0.4439 0.1775 0.4879 0.2122

Task 1: Music Relative Loudness Estimation

Dataset 1

Segment-level Evaluation

Sub code Accuracy Fg-Music_F Bg-Music_F No-Music_F
MMG2 0.8615 0.788 0.821 0.9064

Event-level Evaluation

Sub code Fg-Music_F_500_on Fg-Music_F_500_onoff Fg-Music_F_1000_on Fg-Music_F_1000_onoff Bg-Music_F_500_on Bg-Music_F_500_onoff Bg-Music_F_1000_on Bg-Music_F_1000_onoff Speech_F_500_on Speech_F_500_onoff Speech_F_1000_on Speech_F_1000_onoff
MMG2 0.3298 0.1775 0.4106 0.2742 0.3853 0.1388 0.4463 0.2024 0.5254 0.3123 0.5927 0.3925

Notes on metrics:

<class>_F = segment-level F-measure for the class <class>

<class>_F_500_on = onset-only event-level F-measure (500 ms tolerance) for the class <class>

<class>_F_500_onoff = onset-offset event-level F-measure (500 ms tolerance) for the class <class>

<class>_F_1000_on = onset-only event-level F-measure (1000 ms tolerance) for the class <class>

<class>_F_1000_onoff = onset-offset event-level F-measure (1000 ms tolerance) for the class <class>

Retrieved from "https://music-ir.org/mirex/w/index.php?title=2018:Music_and_or_Speech_Detection_Results&oldid=12703"