The reviewed record of science sign in
Pith

arxiv: 2409.12370 · v1 · pith:BGWWX67D · submitted 2024-09-19 · eess.AS · cs.CL· cs.CV· cs.SD

Robust Audiovisual Speech Recognition Models with Mixture-of-Experts

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:BGWWX67Drecord.jsonopen to challenge →

classification eess.AS cs.CLcs.CVcs.SD
keywords speechvisualrecognitionaudiovisualinformationmodelrobustgeneralization
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.