# AI-generated audio detection on ArtifactBench v1 (test)

Source: [AI-generated audio detection on ArtifactBench v1 (test)](<https://www.sota2.com/research/sota/ai-generated-audio-detection-on-artifactbench-v1-test>)

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

Data updated: 2026-04-20T08:41:32.349Z

Evaluation of model performance for detecting AI-generated audio using the test split of the ArtifactBench v1 dataset, measured by pass/fail rates.

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 | AI-generated audio detection |
| Dataset (including any stated split) | ArtifactBench v1 (test) |
| Metric | Fail Count |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| 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

- [Fail Count](<https://www.sota2.com/research/sota/ai-generated-audio-detection-on-artifactbench-v1-test.md?metric=Fail%20Count>): Lower is better; unit: SCALAR.

- [Pass Rate](<https://www.sota2.com/research/sota/ai-generated-audio-detection-on-artifactbench-v1-test.md?metric=Pass%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Fail Count | Result date | Report paper |
| --- | --- | --- | --- |
| ArtifactNet | 4 | Not recorded | 69e5b32d7d0172140ec7e165 |
| CLAM | 15 | Not recorded | 69e5b32d7d0172140ec7e165 |
| SpecTTTra | 23 | Not recorded | 69e5b32d7d0172140ec7e165 |

### ArtifactNet

Fail Count: 4. Result ID: 69e5e6b847f34ce924cc1f7c.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b32d7d0172140ec7e165.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e5b32d7d0172140ec7e165.md>)

[Implementation](<https://github.com/Intrect-io/artifactbench>)

Recorded evaluation configuration: {"evaluation\_origin":"test"}. This record does not assert independent reproduction.

### CLAM

Fail Count: 15. Result ID: 69e5e6b847f34ce924cc1f7e.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b32d7d0172140ec7e165.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692e72aed6b0dd3342932415.md>)

Recorded evaluation configuration: {"evaluation\_origin":"test"}. This record does not assert independent reproduction.

### SpecTTTra

Fail Count: 23. Result ID: 69e5e6b847f34ce924cc1f7d.

[Reporting paper](<https://www.sota2.com/research/paper/69e5b32d7d0172140ec7e165.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa771b1e209131cea7109c.md>)

Recorded evaluation configuration: {"evaluation\_origin":"test"}. This record does not assert independent reproduction.

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