# Audio Watermark Detection on VoxWatermark (test 2)

Source: [Audio Watermark Detection on VoxWatermark (test 2)](<https://www.sota2.com/research/sota/audio-watermark-detection-on-voxwatermark-test-2>)

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

Data updated: 2026-06-16T07:39:22.444Z

Evaluation of Audio Watermark Detection performance on the specific 'test 2' split of the VoxWatermark dataset, reporting detailed metrics including Overall AUROC, Accuracy, and Precision/Recall/F1 scores for both clean and watermarked audio samples.

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 watermark detection |
| Dataset (including any stated split) | VoxWatermark (test 2) |
| Metric | Overall AUROC |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Overall AUROC](<https://www.sota2.com/research/sota/audio-watermark-detection-on-voxwatermark-test-2.md?metric=Overall%20AUROC>): Higher is better; unit: PERCENT.

- [Overall Accuracy](<https://www.sota2.com/research/sota/audio-watermark-detection-on-voxwatermark-test-2.md?metric=Overall%20Accuracy>): Higher is better; unit: PERCENT.

- [Clean Precision](<https://www.sota2.com/research/sota/audio-watermark-detection-on-voxwatermark-test-2.md?metric=Clean%20Precision>): Higher is better; unit: PERCENT.

- [Clean Recall](<https://www.sota2.com/research/sota/audio-watermark-detection-on-voxwatermark-test-2.md?metric=Clean%20Recall>): Higher is better; unit: PERCENT.

- [Clean F1 Score](<https://www.sota2.com/research/sota/audio-watermark-detection-on-voxwatermark-test-2.md?metric=Clean%20F1%20Score>): Higher is better; unit: PERCENT.

- [Watermarked Precision](<https://www.sota2.com/research/sota/audio-watermark-detection-on-voxwatermark-test-2.md?metric=Watermarked%20Precision>): Higher is better; unit: PERCENT.

- [Watermarked Recall](<https://www.sota2.com/research/sota/audio-watermark-detection-on-voxwatermark-test-2.md?metric=Watermarked%20Recall>): Higher is better; unit: PERCENT.

- [Watermarked F1 Score](<https://www.sota2.com/research/sota/audio-watermark-detection-on-voxwatermark-test-2.md?metric=Watermarked%20F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Overall AUROC | Result date | Report paper |
| --- | --- | --- | --- |
| AudioWMD | 63.2 | Not recorded | 6a30d876d33dfb23e783cb59 |
| WMD | 57.9 | Not recorded | 6a30d876d33dfb23e783cb59 |

### AudioWMD

Overall AUROC: 63.2. Result ID: 6a30fd78fbc373592c2ce7c0.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d876d33dfb23e783cb59.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a30d876d33dfb23e783cb59.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### WMD

Overall AUROC: 57.9. Result ID: 6a30fd78fbc373592c2ce7c1.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d876d33dfb23e783cb59.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72bc1e209131cea5841e.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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