# Audio Classification on ImageNet ESC-27

Source: [Audio Classification on ImageNet ESC-27](<https://www.sota2.com/research/sota/audio-classification-on-imagenet-esc-27>)

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

Data updated: 2026-02-26T05:29:54.595Z

Evaluation of audio classification performance using the ImageNet ESC-27 dataset, typically measured by 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 | Audio Classification |
| Dataset (including any stated split) | ImageNet ESC-27 |
| Metric | Accuracy |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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/audio-classification-on-imagenet-esc-27.md?metric=Accuracy>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Audio-Image Linear | 0.485 | Not recorded | 68fa74a71e209131cea62f9b |
| Audio-Only Linear | 0.471 | Not recorded | 68fa74a71e209131cea62f9b |
| Audio-Image Linear | 0.435 | Not recorded | 68fa74a71e209131cea62f9b |
| Audio-Only Linear | 0.39 | Not recorded | 68fa74a71e209131cea62f9b |
| Audio-Image Linear | 0.35 | Not recorded | 68fa74a71e209131cea62f9b |
| Audio-Only Linear | 0.282 | Not recorded | 68fa74a71e209131cea62f9b |

### Audio-Image Linear

Accuracy: 0.485. Result ID: 699353723a6c314849153321.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74a71e209131cea62f9b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74a71e209131cea62f9b.md>)

Recorded evaluation configuration: {"Shots":"4-shot","Audio Encoder":"AudioCLIP (ES-ResNeXT)","Modality":"Cross-modal (Audio + Image)"}. This record does not assert independent reproduction.

### Audio-Only Linear

Accuracy: 0.471. Result ID: 699353723a6c31484915331e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74a71e209131cea62f9b.md>)

Recorded evaluation configuration: {"Shots":"4-shot","Audio Encoder":"AudioCLIP (ES-ResNeXT)"}. This record does not assert independent reproduction.

### Audio-Image Linear

Accuracy: 0.435. Result ID: 699353723a6c314849153320.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74a71e209131cea62f9b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74a71e209131cea62f9b.md>)

Recorded evaluation configuration: {"Shots":"2-shot","Audio Encoder":"AudioCLIP (ES-ResNeXT)","Modality":"Cross-modal (Audio + Image)"}. This record does not assert independent reproduction.

### Audio-Only Linear

Accuracy: 0.39. Result ID: 699353723a6c31484915331d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74a71e209131cea62f9b.md>)

Recorded evaluation configuration: {"Shots":"2-shot","Audio Encoder":"AudioCLIP (ES-ResNeXT)"}. This record does not assert independent reproduction.

### Audio-Image Linear

Accuracy: 0.35. Result ID: 699353723a6c31484915331f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74a71e209131cea62f9b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74a71e209131cea62f9b.md>)

Recorded evaluation configuration: {"Shots":"1-shot","Audio Encoder":"AudioCLIP (ES-ResNeXT)","Modality":"Cross-modal (Audio + Image)"}. This record does not assert independent reproduction.

### Audio-Only Linear

Accuracy: 0.282. Result ID: 699353723a6c31484915331c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74a71e209131cea62f9b.md>)

Recorded evaluation configuration: {"Shots":"1-shot","Audio Encoder":"AudioCLIP (ES-ResNeXT)"}. This record does not assert independent reproduction.

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