# Voice Activity Detection on WenetSpeech internal (test)

Source: [Voice Activity Detection on WenetSpeech internal (test)](<https://www.sota2.com/research/sota/voice-activity-detection-on-wenetspeech-internal-test>)

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

Data updated: 2026-04-23T08:37:25.497Z

Evaluation of Voice Activity Detection performance on the internal test split of the WenetSpeech dataset, measured using Accuracy, Precision, Recall, 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 | Voice Activity Detection |
| Dataset (including any stated split) | WenetSpeech internal (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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/voice-activity-detection-on-wenetspeech-internal-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/voice-activity-detection-on-wenetspeech-internal-test.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/voice-activity-detection-on-wenetspeech-internal-test.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1-score](<https://www.sota2.com/research/sota/voice-activity-detection-on-wenetspeech-internal-test.md?metric=F1-score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Silero-VAD | 95.56 | Not recorded | 69e85be87d0172140ec81188 |
| TEN-VAD | 94.79 | Not recorded | 69e85be87d0172140ec81188 |
| UAF-30B-A3B | 92.31 | Not recorded | 69e85be87d0172140ec81188 |
| FSMN-VAD | 91.13 | Not recorded | 69e85be87d0172140ec81188 |

### Silero-VAD

Accuracy: 95.56. Result ID: 69e9d9a247f34ce924d10641.

[Reporting paper](<https://www.sota2.com/research/paper/69e85be87d0172140ec81188.md>)

Recorded evaluation configuration: {"streaming settings":"600 ms chunks"}. This record does not assert independent reproduction.

### TEN-VAD

Accuracy: 94.79. Result ID: 69e9d9a247f34ce924d10642.

[Reporting paper](<https://www.sota2.com/research/paper/69e85be87d0172140ec81188.md>)

Recorded evaluation configuration: {"streaming settings":"600 ms chunks"}. This record does not assert independent reproduction.

### UAF-30B-A3B

Accuracy: 92.31. Result ID: 69e9d9a247f34ce924d10643.

[Reporting paper](<https://www.sota2.com/research/paper/69e85be87d0172140ec81188.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e85be87d0172140ec81188.md>)

Recorded evaluation configuration: {"streaming settings":"600 ms chunks"}. This record does not assert independent reproduction.

### FSMN-VAD

Accuracy: 91.13. Result ID: 69e9d9a247f34ce924d10640.

[Reporting paper](<https://www.sota2.com/research/paper/69e85be87d0172140ec81188.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64231e209131cea02c1b.md>)

Recorded evaluation configuration: {"streaming settings":"600 ms chunks"}. This record does not assert independent reproduction.

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