Junyan: MIREX 2026 Audio Chord Estimation results

2026-10-14T18:55:08Z

MIREX 2026 Audio Chord Estimation results

New page

= Submissions =

{| class="wikitable"
|-
! Submission
! Title
! PDF
! Authors
|-
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | Baseline: Chordino
| 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]
|
|-
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | Baseline: ChordFormer
| style="vertical-align:bottom; background-color:#F8F9FA; color:#222;" | ChordFormer: A Conformer-Based Architecture for Large-Vocabulary Audio Chord Recognition
| [https://github.com/mwaseemrandhawa/ChordFormer Link]
|
|-
| ChordyV-ACE
| ChordyV: A Hybrid Acoustic-Harmonic Audio Chord Estimation System with Metric Synchronization
| [http://futuremirex.com/portal/wp-content/uploads/2026/audio-chord-estimation/ChordyV-ACE.pdf PDF]
| Mulfie Ansyori Sofyan
|-
| MuQ-BTC
| Audio Chord Estimation Using the SheetSage-Chord Dataset, Pre-trained Features, and Source Separation
| [http://futuremirex.com/portal/wp-content/uploads/2026/audio-chord-estimation/MuQ-BTC.pdf PDF]
| Marco Viviani, Xinwei Jiang, Zhongyi Huang, Alexandre D'Hooge, Yulun Wu, Yaolong Ju
|-
| SLASH
| SLASH: Audio Chord Estimation with Harmonic Features and Structured Decoding
| [http://futuremirex.com/portal/wp-content/uploads/2026/audio-chord-estimation/SLASH.pdf PDF]
| Mehmet Akif Vardar
|}

= 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 (161 songs), containing mainly western pop songs from the Billboard chart.
* '''Yamaha_JPop''': A private dataset annotated by Yamaha Corporation (250 JPOP songs).
* '''Yamaha_Balanced''': A private dataset annotated by Yamaha Corporation (239 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%).
* '''JSIR''': to be announced.

====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 (188 songs).
* '''RWC Popular''': 100 pop songs from the RWC (Real World Computing) Music Database. 20% songs with English lyrics and 80% songs with Japanese lyrics.
* '''JAAH''' (new in 2026): 113 jazz recordings of the [https://github.com/MTG/JAAH Jazz Audio-Aligned Harmony] dataset, with the official published chord annotations.

= Main Results =

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

For each metric, the best result is shown in bold. Entries marked * were trained or tuned on that dataset and are not ranked on it.

== Billboard2013 ==

{| class="wikitable" style="text-align:right;"
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | ChordyV-ACE
| 54.88
| 37.58
| 32.99
| 25.81
| 22.16
| 70.33
| 78.49
| 67.62
|- style="vertical-align:bottom;"
| style="text-align:left;" | MuQ-BTC
| 78.04
| 74.67
| 72.37
| 62.45
| 60.31
| 84.50
| '''89.67'''
| 82.58
|- style="vertical-align:bottom;"
| style="text-align:left;" | SLASH
| '''82.02'''
| '''80.37'''
| 78.13
| 62.92
| 60.90
| 84.01
| 86.30
| 84.37
|- 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="text-align:left;" | Baseline: ChordFormer
| 81.11
| 80.01
| '''78.98'''
| '''69.02'''
| '''68.13'''
| '''85.22'''
| 82.25
| '''92.03'''
|}


== YAMAHA_Balanced ==

{| class="wikitable" style="text-align:right;"
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | ChordyV-ACE
|
|
|
|
|
|
|
|
|- style="vertical-align:bottom;"
| style="text-align:left;" | MuQ-BTC
|
|
|
|
|
|
|
|
|- style="vertical-align:bottom;"
| style="text-align:left;" | SLASH
|
|
|
|
|
|
|
|
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
|
|
|
|
|
|
|
|
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ChordFormer
|
|
|
|
|
|
|
|
|}

== YAMAHA_JPop ==

{| class="wikitable" style="text-align:right;"
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | ChordyV-ACE
|
|
|
|
|
|
|
|
|- style="vertical-align:bottom;"
| style="text-align:left;" | MuQ-BTC
|
|
|
|
|
|
|
|
|- style="vertical-align:bottom;"
| style="text-align:left;" | SLASH
|
|
|
|
|
|
|
|
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
|
|
|
|
|
|
|
|
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ChordFormer
|
|
|
|
|
|
|
|
|}


== JSIR ==

{| class="wikitable" style="text-align:right;"
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | ChordyV-ACE
|
|
|
|
|
|
|
|
|- style="vertical-align:bottom;"
| style="text-align:left;" | MuQ-BTC
|
|
|
|
|
|
|
|
|- style="vertical-align:bottom;"
| style="text-align:left;" | SLASH
|
|
|
|
|
|
|
|
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
|
|
|
|
|
|
|
|
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ChordFormer
|
|
|
|
|
|
|
|
|}

= 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 ==

{| class="wikitable" style="text-align:right;"
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | ChordyV-ACE
| 57.87
| 40.63
| 35.85
| 28.47
| 24.68
| 71.13
| 79.43
| 67.60
|- style="vertical-align:bottom;"
| style="text-align:left;" | MuQ-BTC
| '''81.86'''
| '''79.81'''
| '''77.39'''
| '''67.42'''
| '''64.95'''
| '''85.98'''
| '''90.77'''
| '''83.81'''
|- style="vertical-align:bottom;"
| style="text-align:left;" | SLASH*
| 84.54
| 83.86
| 81.57
| 68.86
| 66.70
| 85.94
| 88.87
| 84.32
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 74.04
| 72.11
| 70.05
| 55.24
| 53.28
| 83.69
| 85.33
| 83.48
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ChordFormer*
| 86.29
| 85.91
| 84.74
| 78.50
| 77.48
| 89.23
| 87.00
| 92.37
|}

<nowiki>*</nowiki> Trained on this dataset: SLASH (public McGill Billboard annotations); Baseline ChordFormer (the 1,217-song set of Humphrey and Bello, which includes the public McGill Billboard songs).

== RWC-Popular ==

{| class="wikitable" style="text-align:right;"
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | ChordyV-ACE
| 63.55
| 46.76
| 44.17
| 34.02
| 31.99
| 78.88
| 80.09
| 79.23
|- style="vertical-align:bottom;"
| style="text-align:left;" | MuQ-BTC*
| 88.81
| 86.65
| 80.48
| 75.74
| 69.55
| 91.55
| 94.82
| 89.64
|- style="vertical-align:bottom;"
| style="text-align:left;" | SLASH*
| 89.66
| 89.02
| 85.15
| 71.56
| 68.25
| 89.43
| 92.37
| 86.94
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| '''78.97'''
| '''77.78'''
| '''74.13'''
| '''63.15'''
| '''59.72'''
| '''88.64'''
| '''88.07'''
| '''89.76'''
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ChordFormer*
| 89.05
| 87.70
| 86.17
| 75.80
| 74.43
| 92.21
| 90.21
| 94.64
|}

<nowiki>*</nowiki> Trained on this dataset: SLASH (MARL-Chords annotations of the RWC Popular songs); MuQ-BTC (RWC-Pop, 80% of the songs in the submitted fold); Baseline ChordFormer (the 1,217-song set of Humphrey and Bello, which includes RWC Popular).

== JAAH ==

{| class="wikitable" style="text-align:right;"
|- style="font-weight:bold; text-align:left;"
! style="vertical-align:bottom;" | Group
! style="vertical-align:bottom;" | MirexRoot
! style="vertical-align:bottom;" | MirexMajMin
! style="vertical-align:bottom;" | MirexMajMinBass
! style="vertical-align:bottom;" | MirexSevenths
! style="vertical-align:bottom;" | MirexSeventhsBass
! style="vertical-align:bottom;" | MeanSeg
! style="vertical-align:bottom;" | UnderSeg
! style="vertical-align:bottom;" | OverSeg
|- style="vertical-align:bottom;"
| style="text-align:left;" | ChordyV-ACE
| 29.37
| 19.93
| 15.04
| 11.21
| 8.21
| 68.08
| 68.62
| 71.74
|- style="vertical-align:bottom;"
| style="text-align:left;" | MuQ-BTC
| 58.64
| 55.74
| 54.74
| 43.58
| 43.26
| '''77.09'''
| '''85.26'''
| 72.65
|- style="vertical-align:bottom;"
| style="text-align:left;" | SLASH*
| 53.97
| 51.61
| 49.17
| 36.29
| 34.80
| 73.61
| 72.75
| 78.23
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: Chordino
| 45.35
| 41.70
| 38.81
| 23.93
| 21.92
| 75.61
| 77.42
| 76.69
|- style="vertical-align:bottom;"
| style="text-align:left;" | Baseline: ChordFormer
| '''60.39'''
| '''59.47'''
| '''57.83'''
| '''46.10'''
| '''45.50'''
| 75.50
| 70.10
| '''86.07'''
|}

<nowiki>*</nowiki> SLASH: decoder settings were tuned on development data that included JAAH songs (the network itself was not trained on JAAH).

= Notes =

* MuQ-BTC was trained on SheetSage-Chord, which may overlap with some popular song datasets to a small extent.

2026:Audio Chord Estimation Results - Revision history

Junyan: MIREX 2026 Audio Chord Estimation results