Automatic Speech Recognition on Artificial Dataset Simulative Echo
6.55CERROSE
Evaluation results
| Method | Links | |
|---|---|---|
| ROSEASR Model=W2V22023.12 | 6.55 | |
| ROSE w/o attn.ASR Model=W2V22023.12 | 7.22 | |
| ROSE w/o LASRASR Model=W2V22023.12 | 7.99 | |
| SE-ConformerASR Model=W2V22023.12 | 8.12 | |
| BSRNNASR Model=W2V22023.12 | 8.55 | |
| DCCRN-EASR Model=W2V22023.12 | 9.72 | |
| MixedASR Model=W2V22023.12 | 10.22 | |
| ROSEASR Model=DS22023.12 | 22.31 | |
| ROSE w/o attn.ASR Model=DS22023.12 | 26.56 | |
| ROSE w/o LASRASR Model=DS22023.12 | 29.44 | |
| SE-ConformerASR Model=DS22023.12 | 31.1 | |
| BSRNNASR Model=DS22023.12 | 32.23 | |
| DCCRN-EASR Model=DS22023.12 | 33.67 | |
| MixedASR Model=DS22023.12 | 42.72 |