← Search

Shenjian Wang

2 accepted papers

2023

Practice of the Conformer Enhanced Audio-Visual Hubert on Mandarin and English

ICASSP 2023accepted

Considering the bimodal nature of human speech perception, lips, and teeth movement has a pivotal role in automatic speech recognition. Benefiting from the correlated and noise-invariant visual information, audio-visual recognition systems enhance robustness in multiple scenarios. In previous work,…

Cited by 0SourceScholar