Visual Speech Recognition on GRID corpus (mixed-speech)
Metric: STOI (higher is better)
LeaderboardDataset
Loading chart...
Results
Submit a result| # | Model↕ | STOI▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | Visual Voice Memory | 0.738 | No | - | - | Code |
| 2 | Lip2Wav | 0.731 | No | Learning Individual Speaking Styles for Accurate... | 2020-05-17 | Code |