Audio-Visual Speech Recognition on LRS3 433 h 10 dB SNR
1WERAVUR-LLM
Evaluation Results
| Method | Links | |
|---|---|---|
| AVUR-LLMModality=AV2026.03 | 1 | |
| Whisper-FlamingoModality=AV2026.03 | 1.4 | |
| CMAModality=AV2026.03 | 1.8 | |
| AV-HuBERTModality=AV2026.03 | 2 |
| Method | Links | |
|---|---|---|
| AVUR-LLMModality=AV2026.03 | 1 | |
| Whisper-FlamingoModality=AV2026.03 | 1.4 | |
| CMAModality=AV2026.03 | 1.8 | |
| AV-HuBERTModality=AV2026.03 | 2 |