Spoken Command Recognition 벤치마크
Spoken Command Recognition on Speech Command v2
Accuracy
- 2020-10-21 — COLA: Accuracy 95.5
- 2021-10-19 — SSAST-FRAME: Accuracy 98.1
| Rank | Model | Accuracy | Paper | Code | Year |
|---|---|---|---|---|---|
| 1 | SSAST-FRAME | 98.1 | SSAST: Self-Supervised Audio Spectrogram Transformer | YuanGongND/ast · YuanGongND/ssast · siavashshams/ssamba | 2021 |
| 2 | Base (ours) | 98.0 | ATST: Audio Representation Learning with Teacher-Student Transformer | Audio-WestlakeU/ATST-SED · Audio-WestlakeU/audiossl · 2024-MindSpore-1/Code6 · +1 | 2022 |
| 2 | SSAST-PATCH | 98.0 | SSAST: Self-Supervised Audio Spectrogram Transformer | YuanGongND/ast · YuanGongND/ssast · siavashshams/ssamba | 2021 |
| 4 | COLA | 95.5 | Contrastive Learning of General-Purpose Audio Representations | google-research/google-research · SarthakYadav/audax | 2020 |