Lip to Speech Synthesis on GRID corpus (mixed-speech)
Metric: ESTOI (higher is better)
Metric: ESTOI (higher is better)
| # | Model↕ | ESTOI▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | Visual Voice Memory | 0.579 | No | - | - | Code |
| 2 | Lip2Wav | 0.535 | No | Learning Individual Speaking Styles for Accurate... | 2020-05-17 | Code |