# Speech Emotion Recognition on RAVDESS (6-fold subject-independent CV)

Source: [Speech Emotion Recognition on RAVDESS (6-fold subject-independent CV)](<https://www.sota2.com/research/sota/speech-emotion-recognition-on-ravdess-6-fold-subject-independent-cv>)

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

Data updated: 2026-02-26T06:08:45.591Z

Evaluation of Speech Emotion Recognition performance on the RAVDESS dataset using a 6-fold subject-independent cross-validation scheme, reporting Weighted Accuracy (WA) and Unweighted Accuracy (UA).

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 (6-fold subject-independent cross-validation) |
| Metric | Weighted Accuracy (WA) |
| 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

- [Weighted Accuracy (WA)](<https://www.sota2.com/research/sota/speech-emotion-recognition-on-ravdess-6-fold-subject-independent-cv.md?metric=Weighted%20Accuracy%20(WA)>): Higher is better; unit: PERCENT.

- [Unweighted Accuracy (UA)](<https://www.sota2.com/research/sota/speech-emotion-recognition-on-ravdess-6-fold-subject-independent-cv.md?metric=Unweighted%20Accuracy%20(UA)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Weighted Accuracy (WA) | Result date | Report paper |
| --- | --- | --- | --- |
| Proposed Method | 93.4 | Not recorded | 69326756d6b0dd3342934562 |
| Sun et al. \[33\] | 87.99 | Not recorded | 69326756d6b0dd3342934562 |
| Sadok et al. \[36\] | 84.8 | Not recorded | 69326756d6b0dd3342934562 |
| Yu et al. \[34\] | 81.86 | Not recorded | 69326756d6b0dd3342934562 |
| Chumachenko et al. \[35\] | 79.2 | Not recorded | 69326756d6b0dd3342934562 |
| Chen et al. \[13\] | 75.36 | Not recorded | 69326756d6b0dd3342934562 |
| Baevski et al. \[32\] | 74.38 | Not recorded | 69326756d6b0dd3342934562 |
| Sun et al. \[33\] | 72.29 | Not recorded | 69326756d6b0dd3342934562 |

### Proposed Method

Weighted Accuracy (WA): 93.4. Result ID: 699a0f205698665ec492a901.

[Reporting paper](<https://www.sota2.com/research/paper/69326756d6b0dd3342934562.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69326756d6b0dd3342934562.md>)

Recorded evaluation configuration: {"Modality":"Audio-only"}. This record does not assert independent reproduction.

### Sun et al. \[33\]

Weighted Accuracy (WA): 87.99. Result ID: 699a0f205698665ec492a900.

[Reporting paper](<https://www.sota2.com/research/paper/69326756d6b0dd3342934562.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72c21e209131cea586ee.md>)

Recorded evaluation configuration: {"Modality":"Multi-modal"}. This record does not assert independent reproduction.

### Sadok et al. \[36\]

Weighted Accuracy (WA): 84.8. Result ID: 699a0f205698665ec492a8ff.

[Reporting paper](<https://www.sota2.com/research/paper/69326756d6b0dd3342934562.md>)

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

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

Recorded evaluation configuration: {"Modality":"Multi-modal"}. This record does not assert independent reproduction.

### Yu et al. \[34\]

Weighted Accuracy (WA): 81.86. Result ID: 699a0f205698665ec492a8fd.

[Reporting paper](<https://www.sota2.com/research/paper/69326756d6b0dd3342934562.md>)

Recorded evaluation configuration: {"Modality":"Audio-only"}. This record does not assert independent reproduction.

### Chumachenko et al. \[35\]

Weighted Accuracy (WA): 79.2. Result ID: 699a0f205698665ec492a8fe.

[Reporting paper](<https://www.sota2.com/research/paper/69326756d6b0dd3342934562.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bba1e209131cea2fed0.md>)

[Implementation](<https://github.com/rwightman/pytorch-image-models>)

Recorded evaluation configuration: {"Modality":"Multi-modal"}. This record does not assert independent reproduction.

### Chen et al. \[13\]

Weighted Accuracy (WA): 75.36. Result ID: 699a0f205698665ec492a8fc.

[Reporting paper](<https://www.sota2.com/research/paper/69326756d6b0dd3342934562.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dfa1e209131cea3d210.md>)

[Implementation](<https://aka.ms/wavlm>)

Recorded evaluation configuration: {"Modality":"Audio-only"}. This record does not assert independent reproduction.

### Baevski et al. \[32\]

Weighted Accuracy (WA): 74.38. Result ID: 699a0f205698665ec492a8fa.

[Reporting paper](<https://www.sota2.com/research/paper/69326756d6b0dd3342934562.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68891e209131cea1cc36.md>)

[Implementation](<https://github.com/pytorch/fairseq>)

Recorded evaluation configuration: {"Modality":"Audio-only"}. This record does not assert independent reproduction.

### Sun et al. \[33\]

Weighted Accuracy (WA): 72.29. Result ID: 699a0f205698665ec492a8fb.

[Reporting paper](<https://www.sota2.com/research/paper/69326756d6b0dd3342934562.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72c21e209131cea586ee.md>)

Recorded evaluation configuration: {"Modality":"Audio-only"}. This record does not assert independent reproduction.

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