Visual Speech Recognition on CMLR
8Best CER
VSR model with prediction-based auxiliary tasks
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| 8 | 8.1 | 0.05 | ||
| 8.1 | 8.2 | 0.06 | ||
| 9.1 | 9.1 | 0.05 | ||
2022.02 | 22 | - | - | |
2022.02 | 31.3 | - | - | |
2022.02 | 32.5 | - | - | |
2022.02 | 34 | - | - |
VSR model with prediction-based auxiliary tasks
| Method | Links | |||
|---|---|---|---|---|
| 8 | 8.1 | 0.05 | ||
| 8.1 | 8.2 | 0.06 | ||
| 9.1 | 9.1 | 0.05 | ||
2022.02 | 22 | - | - | |
2022.02 | 31.3 | - | - | |
2022.02 | 32.5 | - | - | |
2022.02 | 34 | - | - |