📊 Showing 5 results | 📏 Metric: WER (%)
| Rank | Model | Paper | WER (%) | Date | Code |
|---|---|---|---|---|---|
| 1 | Demucs (ch2) | ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement | 86.80 | 2022-12-21 | - |
| 2 | Demucs (bf) | ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement | 69.80 | 2022-12-21 | - |
| 3 | DAJA (MVDR,HMA,1000) (Overlapped Speech) | Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments | 62.36 | 2022-07-15 | - |
| 4 | ReVISE (ch2) | ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement | 55.00 | 2022-12-21 | - |
| 5 | ReVISE (bf) | ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement | 52.10 | 2022-12-21 | - |