# Spoken Command Recognition on SPCV2 (test)

Source: [Spoken Command Recognition on SPCV2 (test)](<https://www.sota2.com/research/sota/spoken-command-recognition-on-spcv2-test>)

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

Data updated: 2026-02-26T05:29:17.146Z

Evaluation of Spoken Command Recognition performance on the test split of the SPCV2 dataset, measured using accuracy.

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 | Spoken command recognition |
| Dataset (including any stated split) | SPCV2 (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| 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/spoken-command-recognition-on-spcv2-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SSAST-FRAME | 98.1 | Not recorded | 68fa6fa51e209131cea46ded |
| SSAST-PATCH | 98 | Not recorded | 68fa6fa51e209131cea46ded |
| ATST Base | 98 | Not recorded | 68fa6fa51e209131cea46ded |
| Small-SSAST | 97.7 | Not recorded | 68fa6fa51e209131cea46ded |
| ATST Small | 97.6 | Not recorded | 68fa6fa51e209131cea46ded |
| COLA | 95.5 | Not recorded | 68fa6fa51e209131cea46ded |
| M2D | 95.4 | Not recorded | 68fa71251e209131cea4f7ba |
| ATST-Clip | 95.1 | Not recorded | 68fa71251e209131cea4f7ba |
| ATST-Frame | 94.9 | Not recorded | 68fa71251e209131cea4f7ba |
| BYOL-A-V2 | 93.1 | Not recorded | 68fa71251e209131cea4f7ba |
| SF NFNet-F0 | 93 | Not recorded | 68fa71251e209131cea4f7ba |
| BYOL-A | 92.2 | Not recorded | 68fa71251e209131cea4f7ba |
| COLA | 62.4 | Not recorded | 68fa71251e209131cea4f7ba |

### SSAST-FRAME

Accuracy: 98.1. Result ID: 6990f8ec3a6c31484904b64b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fa51e209131cea46ded.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bbe1e209131cea30081.md>)

[Implementation](<https://github.com/YuanGongND/ssast>)

Recorded evaluation configuration: {"Protocol":"Fine-tuning","Number of parameters":"89M"}. This record does not assert independent reproduction.

### SSAST-PATCH

Accuracy: 98. Result ID: 6990f8ec3a6c31484904b64a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fa51e209131cea46ded.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bbe1e209131cea30081.md>)

[Implementation](<https://github.com/YuanGongND/ssast>)

Recorded evaluation configuration: {"Protocol":"Fine-tuning","Number of parameters":"89M"}. This record does not assert independent reproduction.

### ATST Base

Accuracy: 98. Result ID: 6990f8ec3a6c31484904b64d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fa51e209131cea46ded.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fa51e209131cea46ded.md>)

[Implementation](<https://github.com/Audio-WestlakeU/audiossl>)

Recorded evaluation configuration: {"Protocol":"Fine-tuning","Number of parameters":"86M"}. This record does not assert independent reproduction.

### Small-SSAST

Accuracy: 97.7. Result ID: 6990f8ec3a6c31484904b649.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fa51e209131cea46ded.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bbe1e209131cea30081.md>)

[Implementation](<https://github.com/YuanGongND/ssast>)

Recorded evaluation configuration: {"Protocol":"Fine-tuning","Number of parameters":"23M"}. This record does not assert independent reproduction.

### ATST Small

Accuracy: 97.6. Result ID: 6990f8ec3a6c31484904b64c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fa51e209131cea46ded.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fa51e209131cea46ded.md>)

[Implementation](<https://github.com/Audio-WestlakeU/audiossl>)

Recorded evaluation configuration: {"Protocol":"Fine-tuning","Number of parameters":"22M"}. This record does not assert independent reproduction.

### COLA

Accuracy: 95.5. Result ID: 6990f8ec3a6c31484904b648.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fa51e209131cea46ded.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68881e209131cea1cbde.md>)

[Implementation](<https://github.com/google-research/google-research/tree/master/cola>)

Recorded evaluation configuration: {"Protocol":"Fine-tuning"}. This record does not assert independent reproduction.

### M2D

Accuracy: 95.4. Result ID: 69919dfa3a6c314849096725.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71251e209131cea4f7ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ea91e209131cea4130f.md>)

[Implementation](<https://github.com/nttcslab/m2d>)

Recorded evaluation configuration: {"Protocol":"Linear evaluation"}. This record does not assert independent reproduction.

### ATST-Clip

Accuracy: 95.1. Result ID: 69919dfa3a6c314849096726.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71251e209131cea4f7ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71251e209131cea4f7ba.md>)

[Implementation](<https://github.com/Audio-WestlakeU/audiossl>)

Recorded evaluation configuration: {"Protocol":"Linear evaluation"}. This record does not assert independent reproduction.

### ATST-Frame

Accuracy: 94.9. Result ID: 69919dfa3a6c314849096727.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71251e209131cea4f7ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71251e209131cea4f7ba.md>)

[Implementation](<https://github.com/Audio-WestlakeU/audiossl>)

Recorded evaluation configuration: {"Protocol":"Linear evaluation"}. This record does not assert independent reproduction.

### BYOL-A-V2

Accuracy: 93.1. Result ID: 69919dfa3a6c314849096723.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71251e209131cea4f7ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e9d1e209131cea411ae.md>)

Recorded evaluation configuration: {"Protocol":"Linear evaluation"}. This record does not assert independent reproduction.

### SF NFNet-F0

Accuracy: 93. Result ID: 69919dfa3a6c314849096724.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71251e209131cea4f7ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cd51e209131cea3612c.md>)

Recorded evaluation configuration: {"Protocol":"Linear evaluation"}. This record does not assert independent reproduction.

### BYOL-A

Accuracy: 92.2. Result ID: 69919dfa3a6c314849096722.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71251e209131cea4f7ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69c91e209131cea23fc6.md>)

Recorded evaluation configuration: {"Protocol":"Linear evaluation"}. This record does not assert independent reproduction.

### COLA

Accuracy: 62.4. Result ID: 69919dfa3a6c314849096721.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71251e209131cea4f7ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68881e209131cea1cbde.md>)

[Implementation](<https://github.com/google-research/google-research/tree/master/cola>)

Recorded evaluation configuration: {"Protocol":"Linear evaluation"}. This record does not assert independent reproduction.

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