Audio Visual Speech Recognition On Lrs2
Métriques
Test WER
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Test WER |
|---|---|
| end-to-end-audio-visual-speech-recognition | 3.7 |
| deep-audio-visual-speech-recognition | 8.2 |
| auto-avsr-audio-visual-speech-recognition | 1.5 |
| deep-audio-visual-speech-recognition | 8.5 |
| audio-visual-recognition-of-overlapped-speech | 5.9 |
| whisper-flamingo-integrating-visual-features | 1.4 |
| leveraging-uni-modal-self-supervised-learning-1 | 2.6 |
| audio-visual-speech-recognition-with-a-hybrid | 7.0 |