Audio-Visual Speech-to-Audio Translation on LRS3-T low-resource scenario En-Fr
41.4ASR-BLEUAV2AV
Evaluation Results
| Method | Links | |
|---|---|---|
| AV2AVFinetuning data size=200hr2023.12 | 41.4 | |
| AV2AVFinetuning data size=30hr2023.12 | 37.2 | |
| AV2AVFinetuning data size=10hr2023.12 | 34.7 | |
| AV-TranSpeechFinetuning data size=200hr2023.12 | 33.6 | |
| AV-TranSpeechFinetuning data size=30hr2023.12 | 28.3 | |
| AV2AVFinetuning data size=0hr2023.12 | 27.1 | |
| AV-TranSpeechFinetuning data size=10hr2023.12 | 24.4 |