Lip2Wav
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Lip to Speech | Lip2Wav unconstrained single-speaker 1.0 | STOI0.446 | 15 | |
| Lip-to-speech synthesis | Lip2Wav 1.0 (test) | Intelligibility4.82 | 5 | |
| Audio-Visual Speech Separation and Enhancement | Lip2Wav | PESQ1.482 | 4 | |
| Lip to Speech | Lip2Wav unseen (test) | Mispronunciations21.5 | 3 |
Showing 4 of 4 rows