# Speech Emotion Recognition on RAVDESS-Song (test)

Source: [Speech Emotion Recognition on RAVDESS-Song (test)](<https://www.sota2.com/research/sota/speech-emotion-recognition-on-ravdess-song-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:28:51.734Z

Evaluation of Speech Emotion Recognition performance on the test split of the RAVDESS-Song subset of the RAVDESS dataset, reporting Accuracy and F1-score.

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 | Speech Emotion Recognition |
| Dataset (including any stated split) | RAVDESS-Song (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/speech-emotion-recognition-on-ravdess-song-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/speech-emotion-recognition-on-ravdess-song-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| VQ-MAE-S-12 | 85.8 | Not recorded | 68fa6f281e209131cea4423e |
| VQ-MAE-S-12 | 84.2 | Not recorded | 68fa6f281e209131cea4423e |
| VQ-MAE-S-12 | 84 | Not recorded | 68fa6f281e209131cea4423e |
| VQ-MAE-S-12 | 83.7 | Not recorded | 68fa6f281e209131cea4423e |
| SpecMAE-12 | 54.5 | Not recorded | 68fa6f281e209131cea4423e |

### VQ-MAE-S-12

Accuracy: 85.8. Result ID: 6990a9263a6c314849023ce2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f281e209131cea4423e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f281e209131cea4423e.md>)

[Implementation](<https://samsad35.github.io/VQ-MAE-Speech/>)

Recorded evaluation configuration: {"Masking Strategy":"Frame","Query2Emo":true}. This record does not assert independent reproduction.

### VQ-MAE-S-12

Accuracy: 84.2. Result ID: 6990a9263a6c314849023ce1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f281e209131cea4423e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f281e209131cea4423e.md>)

[Implementation](<https://samsad35.github.io/VQ-MAE-Speech/>)

Recorded evaluation configuration: {"Masking Strategy":"Frame","Query2Emo":false}. This record does not assert independent reproduction.

### VQ-MAE-S-12

Accuracy: 84. Result ID: 6990a9263a6c314849023cdf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f281e209131cea4423e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f281e209131cea4423e.md>)

[Implementation](<https://samsad35.github.io/VQ-MAE-Speech/>)

Recorded evaluation configuration: {"Masking Strategy":"Patch-tf","Query2Emo":false}. This record does not assert independent reproduction.

### VQ-MAE-S-12

Accuracy: 83.7. Result ID: 6990a9263a6c314849023ce0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f281e209131cea4423e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f281e209131cea4423e.md>)

[Implementation](<https://samsad35.github.io/VQ-MAE-Speech/>)

Recorded evaluation configuration: {"Masking Strategy":"Patch-tf","Query2Emo":true}. This record does not assert independent reproduction.

### SpecMAE-12

Accuracy: 54.5. Result ID: 6990a9263a6c314849023cde.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f281e209131cea4423e.md>)

Recorded evaluation configuration: {"Masking Strategy":"Patch-tf"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.