# Automatic Chord Estimation on ACR (test) Source: [Automatic Chord Estimation on ACR (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:51:35.868Z Evaluation of Automatic Chord Estimation performance on the ACR test set, reporting detailed metrics covering chord quality (e.g., Maj, Min, Dim, Aug, Sus) and structural components (Root, Thirds, 7ths), alongside MIREX and ACQA scores. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Automatic Chord Estimation | | Dataset (including any stated split) | ACR (test) | | Metric | Root Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 8 of 8 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Root Accuracy](): Higher is better; unit: PERCENT. - [Thirds Accuracy](): Higher is better; unit: PERCENT. - [Triads Accuracy](): Higher is better; unit: PERCENT. - [7ths Accuracy](): Higher is better; unit: PERCENT. - [Tetrads Accuracy](): Higher is better; unit: PERCENT. - [Maj/Min Accuracy](): Higher is better; unit: PERCENT. - [MIREX Score](): Higher is better; unit: PERCENT. - [Segmentation Accuracy](): Higher is better; unit: PERCENT. - [Major Chord Accuracy](): Higher is better; unit: PERCENT. - [Minor Chord Accuracy](): Higher is better; unit: PERCENT. - [Dominant 7th Accuracy](): Higher is better; unit: PERCENT. - [Major 7th Accuracy](): Higher is better; unit: PERCENT. - [Minor 7th Accuracy](): Higher is better; unit: PERCENT. - [Diminished Chord Accuracy](): Higher is better; unit: PERCENT. - [Diminished 7th Accuracy](): Higher is better; unit: PERCENT. - [Augmented Chord Accuracy](): Higher is better; unit: PERCENT. - [Suspended Chord Accuracy](): Higher is better; unit: PERCENT. - [WCSR Score](): Higher is better; unit: PERCENT. - [ACQA Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Root Accuracy | Result date | Report paper | | --- | --- | --- | --- | | BTC (CL) | 83.03 | Not recorded | 699d30a86017c4460ffab5d9 | | BTC (CL) | 82.14 | Not recorded | 699d30a86017c4460ffab5d9 | | 2E1D (CL) | 81.55 | Not recorded | 699d30a86017c4460ffab5d9 | | BTC (SL) | 81.52 | Not recorded | 699d30a86017c4460ffab5d9 | | 2E1D (CL) | 81.02 | Not recorded | 699d30a86017c4460ffab5d9 | | 2E1D (SL) | 79.39 | Not recorded | 699d30a86017c4460ffab5d9 | | Li et al. | 78.05 | Not recorded | 699d30a86017c4460ffab5d9 | ### BTC (CL) Root Accuracy: 83.03. Result ID: 699e558c5698665ec4158c79. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labels":"Full labels","Strategy":"Data-Incremental Continual Learning","KD alpha":0.3}. This record does not assert independent reproduction. ### BTC (CL) Root Accuracy: 82.14. Result ID: 699e558c5698665ec4158c78. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labels":"50%","Strategy":"Data-Incremental Continual Learning","KD alpha":0.3}. This record does not assert independent reproduction. ### 2E1D (CL) Root Accuracy: 81.55. Result ID: 699e558c5698665ec4158c77. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labels":"Full labels","Strategy":"Data-Incremental Continual Learning","KD alpha":0.3}. This record does not assert independent reproduction. ### BTC (SL) Root Accuracy: 81.52. Result ID: 699e558c5698665ec4158c75. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"3.03M","Strategy":"Traditional supervised learning","Labels":"Full labels"}. This record does not assert independent reproduction. ### 2E1D (CL) Root Accuracy: 81.02. Result ID: 699e558c5698665ec4158c76. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Labels":"50%","Strategy":"Data-Incremental Continual Learning","KD alpha":0.3}. This record does not assert independent reproduction. ### 2E1D (SL) Root Accuracy: 79.39. Result ID: 699e558c5698665ec4158c74. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"2.2M","Strategy":"Traditional supervised learning","Labels":"Full labels"}. This record does not assert independent reproduction. ### Li et al. Root Accuracy: 78.05. Result ID: 699e558c5698665ec4158c73. [Reporting paper]() Recorded evaluation configuration: {"Framework":"Noisy Student"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.