# Single-label environmental sound classification on ESC-50

Source: [Single-label environmental sound classification on ESC-50](<https://www.sota2.com/research/sota/single-label-environmental-sound-classification-on-esc-50>)

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

Data updated: 2026-06-25T08:03:22.619Z

Evaluation of single-label environmental sound classification performance on the ESC-50 dataset, typically reported using Accuracy.

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 | Single-label environmental sound classification |
| Dataset (including any stated split) | ESC-50 |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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/single-label-environmental-sound-classification-on-esc-50.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| MJEPA ViT-g + data scaling | 96.9 | Not recorded | 6a3cb63e206542251d7ca6ca |
| MJEPA ViT-L + data scaling | 96.8 | Not recorded | 6a3cb63e206542251d7ca6ca |
| XKD | 96.5 | Not recorded | 6a3cb63e206542251d7ca6ca |
| AJEPA | 96.3 | Not recorded | 6a3cb63e206542251d7ca6ca |
| SSLAM | 96.2 | Not recorded | 6a3cb63e206542251d7ca6ca |
| EquiAV | 96 | Not recorded | 6a3cb63e206542251d7ca6ca |
| MJEPA ViT-L | 95.2 | Not recorded | 6a3cb63e206542251d7ca6ca |
| MAViL | 94.4 | Not recorded | 6a3cb63e206542251d7ca6ca |
| XKD | 93.6 | Not recorded | 6a3cb63e206542251d7ca6ca |
| SSLAM | 93.2 | Not recorded | 6a3cb63e206542251d7ca6ca |
| EquiAV | 93.2 | Not recorded | 6a3cb63e206542251d7ca6ca |
| Dasheng-1.2B | 92.2 | Not recorded | 6a3cb63e206542251d7ca6ca |
| MAViL | 90.8 | Not recorded | 6a3cb63e206542251d7ca6ca |
| SPEAR | 89.4 | Not recorded | 6a3cb63e206542251d7ca6ca |
| CAV-MAE Sync | 89.2 | Not recorded | 6a3cb63e206542251d7ca6ca |
| CAV-MAE | 77.5 | Not recorded | 6a3cb63e206542251d7ca6ca |
| AJEPA | 74.4 | Not recorded | 6a3cb63e206542251d7ca6ca |

### MJEPA ViT-g + data scaling

Accuracy: 96.9. Result ID: 6a3ce0b8fbc373592c51efef.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

Recorded evaluation configuration: {"Evaluation protocol":"Frozen feature probing","Params":"1B","Modality":"A+V","Pre-train data":"AS+VM2M"}. This record does not assert independent reproduction.

### MJEPA ViT-L + data scaling

Accuracy: 96.8. Result ID: 6a3ce0b8fbc373592c51efee.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

Recorded evaluation configuration: {"Evaluation protocol":"Frozen feature probing","Params":"300M","Modality":"A+V","Pre-train data":"AS+VM2M"}. This record does not assert independent reproduction.

### XKD

Accuracy: 96.5. Result ID: 6a3ce0b8fbc373592c51eff3.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71a91e209131cea52685.md>)

[Implementation](<https://pritamqu.github.io/XKD>)

Recorded evaluation configuration: {"Evaluation protocol":"Full-model finetuning","Params":"170M","Modality":"A+V","Pre-train data":"AS"}. This record does not assert independent reproduction.

### AJEPA

Accuracy: 96.3. Result ID: 6a3ce0b8fbc373592c51eff0.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d41e209131cea533c4.md>)

Recorded evaluation configuration: {"Evaluation protocol":"Full-model finetuning","Params":"85M","Modality":"A","Pre-train data":"AS"}. This record does not assert independent reproduction.

### SSLAM

Accuracy: 96.2. Result ID: 6a3ce0b8fbc373592c51eff1.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79741e209131cea7db8d.md>)

[Implementation](<https://github.com/ta012/SSLAM>)

Recorded evaluation configuration: {"Evaluation protocol":"Full-model finetuning","Params":"88M","Modality":"A","Pre-train data":"AS"}. This record does not assert independent reproduction.

### EquiAV

Accuracy: 96. Result ID: 6a3ce0b8fbc373592c51eff4.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73c31e209131cea5e53c.md>)

[Implementation](<https://github.com/JongSuk1/EquiAV>)

Recorded evaluation configuration: {"Evaluation protocol":"Full-model finetuning","Params":"170M","Modality":"A+V","Pre-train data":"AS"}. This record does not assert independent reproduction.

### MJEPA ViT-L

Accuracy: 95.2. Result ID: 6a3ce0b8fbc373592c51efed.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

Recorded evaluation configuration: {"Evaluation protocol":"Frozen feature probing","Params":"300M","Modality":"A+V","Pre-train data":"AS"}. This record does not assert independent reproduction.

### MAViL

Accuracy: 94.4. Result ID: 6a3ce0b8fbc373592c51eff2.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa700d1e209131cea48e29.md>)

[Implementation](<https://github.com/facebookresearch/MAViL>)

Recorded evaluation configuration: {"Evaluation protocol":"Full-model finetuning","Params":"170M","Modality":"A+V","Pre-train data":"IN+AS"}. This record does not assert independent reproduction.

### XKD

Accuracy: 93.6. Result ID: 6a3ce0b8fbc373592c51efea.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71a91e209131cea52685.md>)

[Implementation](<https://pritamqu.github.io/XKD>)

Recorded evaluation configuration: {"Evaluation protocol":"Frozen feature probing","Params":"170M","Modality":"A+V","Pre-train data":"AS"}. This record does not assert independent reproduction.

### SSLAM

Accuracy: 93.2. Result ID: 6a3ce0b8fbc373592c51efe5.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79741e209131cea7db8d.md>)

[Implementation](<https://github.com/ta012/SSLAM>)

Recorded evaluation configuration: {"Evaluation protocol":"Frozen feature probing","Params":"88M","Modality":"A","Pre-train data":"AS"}. This record does not assert independent reproduction.

### EquiAV

Accuracy: 93.2. Result ID: 6a3ce0b8fbc373592c51efeb.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73c31e209131cea5e53c.md>)

[Implementation](<https://github.com/JongSuk1/EquiAV>)

Recorded evaluation configuration: {"Evaluation protocol":"Frozen feature probing","Params":"170M","Modality":"A+V","Pre-train data":"AS"}. This record does not assert independent reproduction.

### Dasheng-1.2B

Accuracy: 92.2. Result ID: 6a3ce0b8fbc373592c51efe7.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73931e209131cea5d51d.md>)

Recorded evaluation configuration: {"Evaluation protocol":"Frozen feature probing","Params":"1.2B","Modality":"A","Pre-train data":"272k hrs mix"}. This record does not assert independent reproduction.

### MAViL

Accuracy: 90.8. Result ID: 6a3ce0b8fbc373592c51efe9.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa700d1e209131cea48e29.md>)

[Implementation](<https://github.com/facebookresearch/MAViL>)

Recorded evaluation configuration: {"Evaluation protocol":"Frozen feature probing","Params":"170M","Modality":"A+V","Pre-train data":"IN+AS"}. This record does not assert independent reproduction.

### SPEAR

Accuracy: 89.4. Result ID: 6a3ce0b8fbc373592c51efe6.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690442703ef7ccd74e5e4ac8.md>)

Recorded evaluation configuration: {"Evaluation protocol":"Frozen feature probing","Params":"600M","Modality":"A","Pre-train data":"197k hrs mix"}. This record does not assert independent reproduction.

### CAV-MAE Sync

Accuracy: 89.2. Result ID: 6a3ce0b8fbc373592c51efec.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78b41e209131cea79dbd.md>)

Recorded evaluation configuration: {"Evaluation protocol":"Frozen feature probing","Params":"170M","Modality":"A+V","Pre-train data":"AS"}. This record does not assert independent reproduction.

### CAV-MAE

Accuracy: 77.5. Result ID: 6a3ce0b8fbc373592c51efe8.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f041e209131cea4345b.md>)

[Implementation](<https://github.com/yuangongnd/cav-mae>)

Recorded evaluation configuration: {"Evaluation protocol":"Frozen feature probing","Params":"170M","Modality":"A+V","Pre-train data":"IN+AS"}. This record does not assert independent reproduction.

### AJEPA

Accuracy: 74.4. Result ID: 6a3ce0b8fbc373592c51efe4.

[Reporting paper](<https://www.sota2.com/research/paper/6a3cb63e206542251d7ca6ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d41e209131cea533c4.md>)

Recorded evaluation configuration: {"Evaluation protocol":"Frozen feature probing","Params":"85M","Modality":"A","Pre-train data":"AS"}. This record does not assert independent reproduction.

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