Difference between revisions of "2025:Audio Chord Estimation Results"

From MIREX Wiki
 
(8 intermediate revisions by the same user not shown)
Line 1: Line 1:
−
This page is still WIP. More submissions and descriptions may appear.
 
  
 
= Submissions =
 
= Submissions =
Line 8: Line 7:
 
! Title
 
! Title
 
! PDF
 
! PDF
 +
! Authors
 
|-
 
|-
 
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | Baseline: Chordino
 
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | Baseline: Chordino
 
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | NNLS Chroma v1.1
 
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | NNLS Chroma v1.1
 
| [https://github.com/ismir-mirex/ace-task-captain-notes?tab=readme-ov-file#baselines Link]
 
| [https://github.com/ismir-mirex/ace-task-captain-notes?tab=readme-ov-file#baselines Link]
 +
|
 
|-
 
|-
 
| Baseline: ISMIR2019
 
| Baseline: ISMIR2019
 
| Large-Vocabulary Chord Transcription via Chord Structure Decomposition
 
| Large-Vocabulary Chord Transcription via Chord Structure Decomposition
 
| [https://github.com/ismir-mirex/ace-task-captain-notes?tab=readme-ov-file#baselines Link]
 
| [https://github.com/ismir-mirex/ace-task-captain-notes?tab=readme-ov-file#baselines Link]
 +
|
 
|-
 
|-
 
| MD1
 
| MD1
 
| Degree-Based Automatic Chord Recognition with Enharmonic Distinction
 
| Degree-Based Automatic Chord Recognition with Enharmonic Distinction
 
| TBA
 
| TBA
 +
| Masayuki Doai
 
|-
 
|-
 
| wu-ensemble
 
| wu-ensemble
 
| wu-ensemble
 
| wu-ensemble
 
| TBA
 
| TBA
 +
| Yiwei Ding, Christof Weiß
 
|-
 
|-
 
| wu-single
 
| wu-single
 
| wu-single
 
| wu-single
 
| TBA
 
| TBA
 +
| Yiwei Ding, Christof Weiß
 
|-
 
|-
 
| YK1
 
| YK1
 
| Semi-Supervised Audio Chord Estimator Based on Disentangled Generative Modeling
 
| Semi-Supervised Audio Chord Estimator Based on Disentangled Generative Modeling
 
| TBA
 
| TBA
 +
| Yiming Wu, Kento Yoshida
 
|-
 
|-
 
| BMACE
 
| BMACE
 
| A Mamba-Based Model for Automatic Chord Recognition
 
| A Mamba-Based Model for Automatic Chord Recognition
 
| TBA
 
| TBA
 +
| Chunyu Yuan, Jiyeoung Sim, Johanna Devaney
 
|}
 
|}
  
−
= Main Evaluation Results =
+
= Test Sets =
 +
 
 +
====Main Test Sets====
 +
 
 +
The following datasets are served as pure test sets. No system is allowed to train on them.
 +
 
 +
* '''Billboard 2013''': The held-out portion of the McGill Billboard dataset, containing mainly western pop songs from the Billboard chart.
 +
* '''Yamaha_JPOP''': A private dataset annotated by Yamaha Corporation. The dataset contains 200 JPOP songs.
 +
* '''Yamaha_Balanced''': A private dataset annotated by Yamaha Corporation. The dataset contains 241 songs. While it is still biased towards JPOP songs, the dataset covers a wider range of genres: J.Pop (10.37%), Rock (10.37%), J.Enka (10.37%), J.Kayoukyoku (10.37%), Soundtrack (10.37%), Western Pop (10.37%), Children's Song (10.37%), R&B (6.22%), Hiphop (4.56%), Jazz (2.49%), Dance (2.49%), World (2.07%), Techno (1.24%), Easy listening (1.24%), J.Minyou (1.24%), Others (5.81%).
 +
 
 +
====Additional Test Sets====
 +
 
 +
These are datasets that may not be strictly held-out test sets. Some models might have been trained on these datasets; for specific details, please refer to the extended abstracts of each model.
 +
 
 +
* '''Billboard 2012''': The public portion of the McGill Billboard dataset.
 +
* '''RWC Popular''': 100 pop songs from the RWC (Real World Computing) Music Database. 20% songs with English lyrics and 80% songs with Japanese lyrics.
 +
 
 +
= Main Results =
  
 
The following datasets are served as pure test sets. No system is allowed to train on them.
 
The following datasets are served as pure test sets. No system is allowed to train on them.
Line 56: Line 80:
 
! style="vertical-align:bottom;" | OverSeg
 
! style="vertical-align:bottom;" | OverSeg
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
−
| style="text-align:left;" | Baseline: Chordino
+
| style="text-align:left;" | BMACE
−
| 71.06
+
| 55.72
−
| 67.18
+
| 8.88
−
| 65.09
+
| 8.70
−
| 48.88
+
| 2.52
−
| 47.06
+
| 2.45
−
| 0.82
+
| 68.16
−
| 0.83
+
| 90.86
−
| 0.83
+
| 56.60
−
|- style="vertical-align:bottom;"
 
−
| style="text-align:left;" | Baseline: ISMIR2019
 
−
| 78.61
 
−
| 76.39
 
−
| 74.72
 
−
| 64.15
 
−
| 62.65
 
−
| 0.83
 
−
| 0.79
 
−
| 0.93
 
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
 
| style="text-align:left;" | MD1
 
| style="text-align:left;" | MD1
Line 82: Line 96:
 
| 66.40
 
| 66.40
 
| 65.33
 
| 65.33
−
| 0.86
+
| 86.17
−
| 0.85
+
| 85.50
−
| 0.89
+
| 88.89
 +
|- style="vertical-align:bottom;"
 +
| style="text-align:left;" | YK1
 +
| 81.01
 +
| 78.10
 +
| 75.41
 +
| 64.53
 +
| 62.05
 +
| 85.50
 +
| 85.08
 +
| 87.49
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
 
| style="text-align:left;" | wu-ensemble
 
| style="text-align:left;" | wu-ensemble
Line 92: Line 116:
 
| 55.06
 
| 55.06
 
| 53.96
 
| 53.96
−
| 0.83
+
| 83.19
−
| 0.86
+
| 86.29
−
| 0.82
+
| 82.20
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
 
| style="text-align:left;" | wu-single
 
| style="text-align:left;" | wu-single
Line 102: Line 126:
 
| 55.41
 
| 55.41
 
| 54.15
 
| 54.15
−
| 0.83
+
| 83.16
−
| 0.85
+
| 85.44
−
| 0.83
+
| 83.08
 +
|- style="vertical-align:bottom;"
 +
| style="text-align:left;" | Baseline: Chordino
 +
| 71.06
 +
| 67.18
 +
| 65.09
 +
| 48.88
 +
| 47.06
 +
| 81.60
 +
| 83.14
 +
| 82.71
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
−
| style="text-align:left;" | YK1
+
| style="text-align:left;" | Baseline: ISMIR2019
−
| 81.01
+
| 78.61
−
| 78.10
+
| 76.39
−
| 75.41
+
| 74.72
−
| 64.53
+
| 64.15
−
| 62.05
+
| 62.65
−
| 0.86
+
| 83.39
−
| 0.85
+
| 78.57
−
| 0.87
+
| 92.78
 
|}
 
|}
  
Line 131: Line 165:
 
! style="vertical-align:bottom;" | OverSeg
 
! style="vertical-align:bottom;" | OverSeg
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
−
| style="text-align:left;" | Baseline: Chordino
+
| style="text-align:left;" | BMACE
−
| 77.57
+
| 58.92
−
| 74.64
+
| 12.59
−
| 71.59
+
| 12.29
−
| 56.38
+
| 4.52
−
| 53.90
+
| 4.34
−
| 0.87
+
| 71.62
−
| 0.87
+
| 91.05
−
| 0.87
+
| 60.47
−
|- style="vertical-align:bottom;"
 
−
| style="text-align:left;" | Baseline: ISMIR2019
 
−
| 82.00
 
−
| 81.16
 
−
| 79.69
 
−
| 66.97
 
−
| 65.77
 
−
| 0.89
 
−
| 0.86
 
−
| 0.93
 
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
 
| style="text-align:left;" | MD1
 
| style="text-align:left;" | MD1
Line 157: Line 181:
 
| 64.13
 
| 64.13
 
| 63.14
 
| 63.14
−
| 0.88
+
| 88.09
−
| 0.89
+
| 88.67
−
| 0.88
+
| 88.47
 +
|- style="vertical-align:bottom;"
 +
| style="text-align:left;" | YK1
 +
| 82.53
 +
| 79.71
 +
| 75.60
 +
| 66.02
 +
| 62.31
 +
| 88.94
 +
| 89.78
 +
| 89.33
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
 
| style="text-align:left;" | wu-ensemble
 
| style="text-align:left;" | wu-ensemble
Line 167: Line 201:
 
| 62.84
 
| 62.84
 
| 60.84
 
| 60.84
−
| 0.87
+
| 87.48
−
| 0.89
+
| 88.68
−
| 0.87
+
| 87.43
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
 
| style="text-align:left;" | wu-single
 
| style="text-align:left;" | wu-single
Line 177: Line 211:
 
| 61.60
 
| 61.60
 
| 59.84
 
| 59.84
−
| 0.87
+
| 87.03
−
| 0.90
+
| 89.81
−
| 0.86
+
| 85.89
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
−
| style="text-align:left;" | YK1
+
| style="text-align:left;" | Baseline: Chordino
−
| 82.53
+
| 77.57
−
| 79.71
+
| 74.64
−
| 75.60
+
| 71.59
−
| 66.02
+
| 56.38
−
| 62.31
+
| 53.90
−
| 0.89
+
| 86.51
−
| 0.90
+
| 87.25
−
| 0.89
+
| 87.48
 +
|- style="vertical-align:bottom;"
 +
| style="text-align:left;" | Baseline: ISMIR2019
 +
| 82.00
 +
| 81.16
 +
| 79.69
 +
| 66.97
 +
| 65.77
 +
| 89.04
 +
| 86.43
 +
| 93.49
 
|}
 
|}
  
Line 206: Line 250:
 
! style="vertical-align:bottom;" | OverSeg
 
! style="vertical-align:bottom;" | OverSeg
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
−
| style="text-align:left;" | Baseline: Chordino
+
| style="text-align:left;" | BMACE
−
| 74.49
+
| 52.38
−
| 71.99
+
| 11.90
−
| 69.24
+
| 11.65
−
| 52.40
+
| 2.37
−
| 49.97
+
| 2.23
−
| 0.87
+
| 71.98
−
| 0.86
+
| 90.23
−
| 0.88
+
| 60.42
−
|- style="vertical-align:bottom;"
 
−
| style="text-align:left;" | Baseline: ISMIR2019
 
−
| 81.49
 
−
| 79.99
 
−
| 78.58
 
−
| 62.81
 
−
| 61.61
 
−
| 0.90
 
−
| 0.87
 
−
| 0.94
 
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
 
| style="text-align:left;" | MD1
 
| style="text-align:left;" | MD1
Line 232: Line 266:
 
| 55.59
 
| 55.59
 
| 54.71
 
| 54.71
−
| 0.88
+
| 88.00
−
| 0.88
+
| 88.13
−
| 0.88
+
| 88.20
 +
|- style="vertical-align:bottom;"
 +
| style="text-align:left;" | YK1
 +
| 80.13
 +
| 77.03
 +
| 72.85
 +
| 61.24
 +
| 57.26
 +
| 89.42
 +
| 89.71
 +
| 89.49
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
 
| style="text-align:left;" | wu-ensemble
 
| style="text-align:left;" | wu-ensemble
Line 242: Line 286:
 
| 54.36
 
| 54.36
 
| 52.58
 
| 52.58
−
| 0.87
+
| 87.22
−
| 0.88
+
| 88.44
−
| 0.87
+
| 86.55
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
 
| style="text-align:left;" | wu-single
 
| style="text-align:left;" | wu-single
Line 252: Line 296:
 
| 55.35
 
| 55.35
 
| 53.60
 
| 53.60
−
| 0.87
+
| 87.19
−
| 0.89
+
| 89.30
−
| 0.86
+
| 85.70
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
−
| style="text-align:left;" | YK1
+
| style="text-align:left;" | Baseline: Chordino
−
| 80.13
+
| 74.49
−
| 77.03
+
| 71.99
−
| 72.85
+
| 69.24
−
| 61.24
+
| 52.40
−
| 57.26
+
| 49.97
−
| 0.89
+
| 86.66
−
| 0.90
+
| 85.89
−
| 0.89
+
| 88.28
 +
|- style="vertical-align:bottom;"
 +
| style="text-align:left;" | Baseline: ISMIR2019
 +
| 81.49
 +
| 79.99
 +
| 78.58
 +
| 62.81
 +
| 61.61
 +
| 90.09
 +
| 87.21
 +
| 93.88
 
|}
 
|}
  
−
= Additional Test Sets =
+
= Additional Results =
−
 
 
−
Below are datasets that are not pure test sets. Some models might have trained on them; please see their extended abstracts for details.
 
  
 +
Below are results on datasets that may not be strictly held-out test sets. Some models might have been trained on these datasets; for specific details, please refer to the extended abstracts of each model.
 
== Billboard2012 ==
 
== Billboard2012 ==
  
Line 285: Line 338:
 
! style="vertical-align:bottom;" | OverSeg
 
! style="vertical-align:bottom;" | OverSeg
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
−
| style="text-align:left;" | Baseline: Chordino
+
| style="text-align:left;" | BMACE
−
| 74.04
+
| 58.45
−
| 72.11
+
| 9.13
−
| 70.05
+
| 9.00
−
| 55.24
+
| 2.91
−
| 53.28
+
| 2.86
−
| 0.84
+
| 69.55
−
| 0.85
+
| 92.02
−
| 0.83
+
| 57.41
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
 
| style="text-align:left;" | MD1
 
| style="text-align:left;" | MD1
Line 301: Line 354:
 
| 74.12
 
| 74.12
 
| 73.12
 
| 73.12
−
| 0.89
+
| 88.80
−
| 0.89
+
| 88.63
−
| 0.90
+
| 89.78
 +
|- style="vertical-align:bottom;"
 +
| style="text-align:left;" | YK1
 +
| 85.90
 +
| 84.66
 +
| 81.81
 +
| 77.22
 +
| 74.45
 +
| 88.43
 +
| 87.88
 +
| 89.58
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
 
| style="text-align:left;" | wu-ensemble
 
| style="text-align:left;" | wu-ensemble
Line 311: Line 374:
 
| 59.99
 
| 59.99
 
| 58.79
 
| 58.79
−
| 0.84
+
| 84.42
−
| 0.88
+
| 87.98
−
| 0.83
+
| 82.57
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
 
| style="text-align:left;" | wu-single
 
| style="text-align:left;" | wu-single
Line 321: Line 384:
 
| 60.23
 
| 60.23
 
| 59.07
 
| 59.07
−
| 0.85
+
| 84.87
−
| 0.87
+
| 87.19
−
| 0.84
+
| 84.24
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
−
| style="text-align:left;" | YK1
+
| style="text-align:left;" | Baseline: Chordino
−
| 85.90
+
| 74.04
−
| 84.66
+
| 72.11
−
| 81.81
+
| 70.05
−
| 77.22
+
| 55.24
−
| 74.45
+
| 53.28
−
| 0.88
+
| 83.69
−
| 0.88
+
| 85.33
−
| 0.90
+
| 83.48
 
|}
 
|}
−
 
  
 
== RWC-Popular ==
 
== RWC-Popular ==
Line 351: Line 413:
 
! style="vertical-align:bottom;" | OverSeg
 
! style="vertical-align:bottom;" | OverSeg
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
−
| style="text-align:left;" | Baseline: Chordino
+
| style="text-align:left;" | BMACE
−
| 78.97
+
| 56.48
−
| 77.78
+
| 11.97
−
| 74.13
+
| 11.78
−
| 63.15
+
| 2.41
−
| 59.72
+
| 2.30
−
| 0.89
+
| 72.59
−
| 0.88
+
| 90.92
−
| 0.90
+
| 61.06
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
 
| style="text-align:left;" | MD1
 
| style="text-align:left;" | MD1
Line 367: Line 429:
 
| 66.53
 
| 66.53
 
| 64.83
 
| 64.83
−
| 0.89
+
| 88.53
−
| 0.89
+
| 88.53
−
| 0.89
+
| 88.84
 +
|- style="vertical-align:bottom;"
 +
| style="text-align:left;" | YK1
 +
| 88.76
 +
| 87.27
 +
| 81.14
 +
| 76.88
 +
| 70.90
 +
| 91.90
 +
| 91.55
 +
| 92.43
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
 
| style="text-align:left;" | wu-ensemble
 
| style="text-align:left;" | wu-ensemble
Line 377: Line 449:
 
| 62.65
 
| 62.65
 
| 60.25
 
| 60.25
−
| 0.88
+
| 87.51
−
| 0.90
+
| 89.95
−
| 0.86
+
| 85.65
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
 
| style="text-align:left;" | wu-single
 
| style="text-align:left;" | wu-single
Line 387: Line 459:
 
| 62.86
 
| 62.86
 
| 60.28
 
| 60.28
−
| 0.88
+
| 87.81
−
| 0.89
+
| 89.47
−
| 0.87
+
| 86.64
 
|- style="vertical-align:bottom;"
 
|- style="vertical-align:bottom;"
−
| style="text-align:left;" | YK1
+
| style="text-align:left;" | Baseline: Chordino
−
| 88.76
+
| 78.97
−
| 87.27
+
| 77.78
−
| 81.14
+
| 74.13
−
| 76.88
+
| 63.15
−
| 70.90
+
| 59.72
−
| 0.92
+
| 88.64
−
| 0.92
+
| 88.07
−
| 0.92
+
| 89.76
 
|}
 
|}
 +
 +
 +
= Task Captain's Note =
 +
 +
* Results on Billboard & RWC Popular are competible with previous years.
 +
* Evaluation tools: https://github.com/ismir-mirex/ace-task-captain-note
 +
* Model Raw outputs: https://github.com/ismir-mirex/ace-output
 +
* Detailed evaluation results: https://github.com/ismir-mirex/ace-results

Latest revision as of 07:10, 9 September 2025

Submissions

Submission Title PDF Authors
Baseline: Chordino NNLS Chroma v1.1 Link
Baseline: ISMIR2019 Large-Vocabulary Chord Transcription via Chord Structure Decomposition Link
MD1 Degree-Based Automatic Chord Recognition with Enharmonic Distinction TBA Masayuki Doai
wu-ensemble wu-ensemble TBA Yiwei Ding, Christof Weiß
wu-single wu-single TBA Yiwei Ding, Christof Weiß
YK1 Semi-Supervised Audio Chord Estimator Based on Disentangled Generative Modeling TBA Yiming Wu, Kento Yoshida
BMACE A Mamba-Based Model for Automatic Chord Recognition TBA Chunyu Yuan, Jiyeoung Sim, Johanna Devaney

Test Sets

Main Test Sets

The following datasets are served as pure test sets. No system is allowed to train on them.

  • Billboard 2013: The held-out portion of the McGill Billboard dataset, containing mainly western pop songs from the Billboard chart.
  • Yamaha_JPOP: A private dataset annotated by Yamaha Corporation. The dataset contains 200 JPOP songs.
  • Yamaha_Balanced: A private dataset annotated by Yamaha Corporation. The dataset contains 241 songs. While it is still biased towards JPOP songs, the dataset covers a wider range of genres: J.Pop (10.37%), Rock (10.37%), J.Enka (10.37%), J.Kayoukyoku (10.37%), Soundtrack (10.37%), Western Pop (10.37%), Children's Song (10.37%), R&B (6.22%), Hiphop (4.56%), Jazz (2.49%), Dance (2.49%), World (2.07%), Techno (1.24%), Easy listening (1.24%), J.Minyou (1.24%), Others (5.81%).

Additional Test Sets

These are datasets that may not be strictly held-out test sets. Some models might have been trained on these datasets; for specific details, please refer to the extended abstracts of each model.

  • Billboard 2012: The public portion of the McGill Billboard dataset.
  • RWC Popular: 100 pop songs from the RWC (Real World Computing) Music Database. 20% songs with English lyrics and 80% songs with Japanese lyrics.

Main Results

The following datasets are served as pure test sets. No system is allowed to train on them.

Billboard2013

Group MirexRoot MirexMajMin MirexMajMinBass MirexSevenths MirexSeventhsBass MeanSeg UnderSeg OverSeg
BMACE 55.72 8.88 8.70 2.52 2.45 68.16 90.86 56.60
MD1 81.35 79.15 77.91 66.40 65.33 86.17 85.50 88.89
YK1 81.01 78.10 75.41 64.53 62.05 85.50 85.08 87.49
wu-ensemble 74.64 71.97 70.72 55.06 53.96 83.19 86.29 82.20
wu-single 75.77 73.14 71.74 55.41 54.15 83.16 85.44 83.08
Baseline: Chordino 71.06 67.18 65.09 48.88 47.06 81.60 83.14 82.71
Baseline: ISMIR2019 78.61 76.39 74.72 64.15 62.65 83.39 78.57 92.78

YAMAHA_Balanced

Group MirexRoot MirexMajMin MirexMajMinBass MirexSevenths MirexSeventhsBass MeanSeg UnderSeg OverSeg
BMACE 58.92 12.59 12.29 4.52 4.34 71.62 91.05 60.47
MD1 81.83 80.22 78.87 64.13 63.14 88.09 88.67 88.47
YK1 82.53 79.71 75.60 66.02 62.31 88.94 89.78 89.33
wu-ensemble 82.54 81.29 78.99 62.84 60.84 87.48 88.68 87.43
wu-single 81.37 79.69 77.61 61.60 59.84 87.03 89.81 85.89
Baseline: Chordino 77.57 74.64 71.59 56.38 53.90 86.51 87.25 87.48
Baseline: ISMIR2019 82.00 81.16 79.69 66.97 65.77 89.04 86.43 93.49

YAMAHA_JPop

Group MirexRoot MirexMajMin MirexMajMinBass MirexSevenths MirexSeventhsBass MeanSeg UnderSeg OverSeg
BMACE 52.38 11.90 11.65 2.37 2.23 71.98 90.23 60.42
MD1 79.34 77.10 76.07 55.59 54.71 88.00 88.13 88.20
YK1 80.13 77.03 72.85 61.24 57.26 89.42 89.71 89.49
wu-ensemble 79.58 77.58 75.57 54.36 52.58 87.22 88.44 86.55
wu-single 78.87 76.56 74.66 55.35 53.60 87.19 89.30 85.70
Baseline: Chordino 74.49 71.99 69.24 52.40 49.97 86.66 85.89 88.28
Baseline: ISMIR2019 81.49 79.99 78.58 62.81 61.61 90.09 87.21 93.88

Additional Results

Below are results on datasets that may not be strictly held-out test sets. Some models might have been trained on these datasets; for specific details, please refer to the extended abstracts of each model.

Billboard2012

Group MirexRoot MirexMajMin MirexMajMinBass MirexSevenths MirexSeventhsBass MeanSeg UnderSeg OverSeg
BMACE 58.45 9.13 9.00 2.91 2.86 69.55 92.02 57.41
MD1 85.11 83.98 82.76 74.12 73.12 88.80 88.63 89.78
YK1 85.90 84.66 81.81 77.22 74.45 88.43 87.88 89.58
wu-ensemble 78.26 77.15 75.58 59.99 58.79 84.42 87.98 82.57
wu-single 79.23 78.21 76.76 60.23 59.07 84.87 87.19 84.24
Baseline: Chordino 74.04 72.11 70.05 55.24 53.28 83.69 85.33 83.48

RWC-Popular

Group MirexRoot MirexMajMin MirexMajMinBass MirexSevenths MirexSeventhsBass MeanSeg UnderSeg OverSeg
BMACE 56.48 11.97 11.78 2.41 2.30 72.59 90.92 61.06
MD1 83.98 81.18 79.42 66.53 64.83 88.53 88.53 88.84
YK1 88.76 87.27 81.14 76.88 70.90 91.90 91.55 92.43
wu-ensemble 81.87 80.30 77.58 62.65 60.25 87.51 89.95 85.65
wu-single 82.48 81.35 78.48 62.86 60.28 87.81 89.47 86.64
Baseline: Chordino 78.97 77.78 74.13 63.15 59.72 88.64 88.07 89.76


Task Captain's Note

Retrieved from "https://www.music-ir.org/mirex/w/index.php?title=2025:Audio_Chord_Estimation_Results&oldid=14763"