Robust Audiovisual Speech Recognition Models with Mixture-of-Experts
Abstract
Visual signals can enhance audiovisual speech recognition accuracy by providing additional contextual information. Given the complexity of visual signals, an audiovisual speech recognition model requires robust generalization capabilities across diverse video scenarios, presenting a significant challenge. In this paper, we introduce EVA, leveraging the mixture-of-Experts for audioVisual ASR to perform robust speech recognition for ``in-the-wild'' videos. Specifically, we first encode visual information into visual tokens sequence and map them into speech space by a lightweight projection. Then, we build EVA upon a robust pretrained speech recognition model, ensuring its generalization ability. Moreover, to incorporate visual information effectively, we inject visual information into the ASR model through a mixture-of-experts module. Experiments show our model achieves state-of-the-art results on three benchmarks, which demonstrates the generalization ability of EVA across diverse video domains.
Cite
@article{arxiv.2409.12370,
title = {Robust Audiovisual Speech Recognition Models with Mixture-of-Experts},
author = {Yihan Wu and Yifan Peng and Yichen Lu and Xuankai Chang and Ruihua Song and Shinji Watanabe},
journal= {arXiv preprint arXiv:2409.12370},
year = {2024}
}
Comments
6 pages, 2 figures, accepted by IEEE Spoken Language Technology Workshop 2024