Audio-visual speech separation on CUAVE (test)
13.3SDRVISUALVOICE
Evaluation results
| Method | Links | |
|---|---|---|
| VISUALVOICESpeaker independence=speaker-independent, Training dataset=VoxCeleb22021.01 | 13.3 | |
| Ephrat et al.Speaker independence=speaker-independent, Training dataset=AV-Speech2021.01 | 12.6 | |
| Casanovas et al.Speaker independence=speaker-dependent2021.01 | 7 | |
| Pu et al.Speaker independence=speaker-dependent2021.01 | 6.2 |