# Audio Quality Assessment on DCASE Task 7 Per-category granularity 2023

Source: [Audio Quality Assessment on DCASE Task 7 Per-category granularity 2023](<https://www.sota2.com/research/sota/audio-quality-assessment-on-dcase-task-7-per-category-granularity-2023>)

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

Data updated: 2026-05-08T07:49:10.551Z

Evaluation of audio quality assessment models using FAD, KAD, and OTAD metrics on the DCASE Task 7 Per-category granularity 2023 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 | Audio Quality Assessment |
| Dataset (including any stated split) | DCASE Task 7 Per-category granularity 2023 |
| Metric | FAD |
| Unit | SCALAR |
| Direction | Lower 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

- [FAD](<https://www.sota2.com/research/sota/audio-quality-assessment-on-dcase-task-7-per-category-granularity-2023.md?metric=FAD>): Lower is better; unit: SCALAR.

- [KAD](<https://www.sota2.com/research/sota/audio-quality-assessment-on-dcase-task-7-per-category-granularity-2023.md?metric=KAD>): Lower is better; unit: SCALAR.

- [OTAD (Raw)](<https://www.sota2.com/research/sota/audio-quality-assessment-on-dcase-task-7-per-category-granularity-2023.md?metric=OTAD%20(Raw)>): Lower is better; unit: SCALAR.

- [OTAD (Agnostic)](<https://www.sota2.com/research/sota/audio-quality-assessment-on-dcase-task-7-per-category-granularity-2023.md?metric=OTAD%20(Agnostic)>): Lower is better; unit: SCALAR.

- [OTAD (Naturalistic)](<https://www.sota2.com/research/sota/audio-quality-assessment-on-dcase-task-7-per-category-granularity-2023.md?metric=OTAD%20(Naturalistic)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | FAD | Result date | Report paper |
| --- | --- | --- | --- |
| EnCodec | 0.059 | Not recorded | 69fd6df65497b3b670c8933a |
| VGGish | 0.113 | Not recorded | 69fd6df65497b3b670c8933a |
| PANNs-CNN14 | 0.451 | Not recorded | 69fd6df65497b3b670c8933a |
| PANNs-WGLM | 0.542 | Not recorded | 69fd6df65497b3b670c8933a |
| CLAP | 0.677 | Not recorded | 69fd6df65497b3b670c8933a |
| AudioMAE | 0.697 | Not recorded | 69fd6df65497b3b670c8933a |

### EnCodec

FAD: 0.059. Result ID: 69fd957347f34ce924e05a0c.

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

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

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

### VGGish

FAD: 0.113. Result ID: 69fd957347f34ce924e05a07.

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

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

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

### PANNs-CNN14

FAD: 0.451. Result ID: 69fd957347f34ce924e05a08.

[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: Not recorded. This record does not assert independent reproduction.

### PANNs-WGLM

FAD: 0.542. Result ID: 69fd957347f34ce924e05a09.

[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: Not recorded. This record does not assert independent reproduction.

### CLAP

FAD: 0.677. Result ID: 69fd957347f34ce924e05a0a.

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

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

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

### AudioMAE

FAD: 0.697. Result ID: 69fd957347f34ce924e05a0b.

[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: Not recorded. This record does not assert independent reproduction.

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