Speech Recognition On Easycom
Metrics
WER (%)
Results
Performance results of various models on this benchmark
Model Name | WER (%) | Paper Title | Repository |
|---|---|---|---|
| Demucs (bf) | 69.8 | ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement | - |
| DAJA (MVDR,HMA,1000) (Overlapped Speech) | 62.36 | Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments | - |
| ReVISE (ch2) | 55.0 | ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement | - |
| ReVISE (bf) | 52.1 | ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement | - |
| Demucs (ch2) | 86.8 | ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement | - |
0 of 5 row(s) selected.