# Artifact Detection on Per-sample diagnostics Cross-class noise

Source: [Artifact Detection on Per-sample diagnostics Cross-class noise](<https://www.sota2.com/research/sota/artifact-detection-on-per-sample-diagnostics-cross-class-noise>)

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

Data updated: 2026-05-08T07:49:10.444Z

Evaluation of Artifact Detection performance using per-sample diagnostic metrics (AUROC and Separation Ratio) on the Cross-class noise dataset.

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 | Artifact Detection |
| Dataset (including any stated split) | Per-sample diagnostics Cross-class noise |
| Metric | AUROC |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [AUROC](<https://www.sota2.com/research/sota/artifact-detection-on-per-sample-diagnostics-cross-class-noise.md?metric=AUROC>): Higher is better; unit: SCALAR.

- [Separation Ratio](<https://www.sota2.com/research/sota/artifact-detection-on-per-sample-diagnostics-cross-class-noise.md?metric=Separation%20Ratio>): Higher is better; unit: SCALAR.

## Recorded results

| Method | AUROC | Result date | Report paper |
| --- | --- | --- | --- |
| VGGish | 0.9969 | Not recorded | 69fd6df65497b3b670c8933a |
| CLAP | 0.9951 | Not recorded | 69fd6df65497b3b670c8933a |
| EnCodec | 0.9642 | Not recorded | 69fd6df65497b3b670c8933a |
| PANNs | 0.8966 | Not recorded | 69fd6df65497b3b670c8933a |
| AudioMAE | 0.8632 | Not recorded | 69fd6df65497b3b670c8933a |

### VGGish

AUROC: 0.9969. Result ID: 69fd957347f34ce924e059e7.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6df65497b3b670c8933a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa631b1e209131ce9fcdc1.md>)

Recorded evaluation configuration: {"epsilon (ε)":"0.05"}. This record does not assert independent reproduction.

### CLAP

AUROC: 0.9951. Result ID: 69fd957347f34ce924e059e9.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6df65497b3b670c8933a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa729e1e209131cea57959.md>)

Recorded evaluation configuration: {"epsilon (ε)":"0.05"}. This record does not assert independent reproduction.

### EnCodec

AUROC: 0.9642. Result ID: 69fd957347f34ce924e059e8.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6df65497b3b670c8933a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6db91e209131cea3b969.md>)

Recorded evaluation configuration: {"epsilon (ε)":"0.05"}. This record does not assert independent reproduction.

### PANNs

AUROC: 0.8966. Result ID: 69fd957347f34ce924e059eb.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6df65497b3b670c8933a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68351e209131cea1ac9d.md>)

[Implementation](<https://github.com/qiuqiangkong/audioset_tagging_cnn>)

Recorded evaluation configuration: {"epsilon (ε)":"0.05"}. This record does not assert independent reproduction.

### AudioMAE

AUROC: 0.8632. Result ID: 69fd957347f34ce924e059ea.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6df65497b3b670c8933a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e581e209131cea3f32e.md>)

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

Recorded evaluation configuration: {"epsilon (ε)":"0.05"}. This record does not assert independent reproduction.

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