AD-AVSR: Asymmetric Dual-stream Enhancement for Robust Audio-Visual Speech Recognition

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xue, Junxiao, Liu, Xiaozhen, Wu, Xuecheng, Yin, Xinyi, Huang, Danlei, Yu, Fei
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909731899047936
author Xue, Junxiao
Liu, Xiaozhen
Wu, Xuecheng
Yin, Xinyi
Huang, Danlei
Yu, Fei
author_facet Xue, Junxiao
Liu, Xiaozhen
Wu, Xuecheng
Yin, Xinyi
Huang, Danlei
Yu, Fei
contents Audio-visual speech recognition (AVSR) combines audio-visual modalities to improve speech recognition, especially in noisy environments. However, most existing methods deploy the unidirectional enhancement or symmetric fusion manner, which limits their capability to capture heterogeneous and complementary correlations of audio-visual data-especially under asymmetric information conditions. To tackle these gaps, we introduce a new AVSR framework termed AD-AVSR based on bidirectional modality enhancement. Specifically, we first introduce the audio dual-stream encoding strategy to enrich audio representations from multiple perspectives and intentionally establish asymmetry to support subsequent cross-modal interactions. The enhancement process involves two key components, Audio-aware Visual Refinement Module for enhanced visual representations under audio guidance, and Cross-modal Noise Suppression Masking Module which refines audio representations using visual cues, collaboratively leading to the closed-loop and bidirectional information flow. To further enhance correlation robustness, we adopt a threshold-based selection mechanism to filter out irrelevant or weakly correlated audio-visual pairs. Extensive experimental results on the LRS2 and LRS3 datasets indicate that our AD-AVSR consistently surpasses SOTA methods in both performance and noise robustness, highlighting the effectiveness of our model design.
format Preprint
id arxiv_https___arxiv_org_abs_2508_07608
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AD-AVSR: Asymmetric Dual-stream Enhancement for Robust Audio-Visual Speech Recognition
Xue, Junxiao
Liu, Xiaozhen
Wu, Xuecheng
Yin, Xinyi
Huang, Danlei
Yu, Fei
Multimedia
Computer Vision and Pattern Recognition
Sound
Audio and Speech Processing
Audio-visual speech recognition (AVSR) combines audio-visual modalities to improve speech recognition, especially in noisy environments. However, most existing methods deploy the unidirectional enhancement or symmetric fusion manner, which limits their capability to capture heterogeneous and complementary correlations of audio-visual data-especially under asymmetric information conditions. To tackle these gaps, we introduce a new AVSR framework termed AD-AVSR based on bidirectional modality enhancement. Specifically, we first introduce the audio dual-stream encoding strategy to enrich audio representations from multiple perspectives and intentionally establish asymmetry to support subsequent cross-modal interactions. The enhancement process involves two key components, Audio-aware Visual Refinement Module for enhanced visual representations under audio guidance, and Cross-modal Noise Suppression Masking Module which refines audio representations using visual cues, collaboratively leading to the closed-loop and bidirectional information flow. To further enhance correlation robustness, we adopt a threshold-based selection mechanism to filter out irrelevant or weakly correlated audio-visual pairs. Extensive experimental results on the LRS2 and LRS3 datasets indicate that our AD-AVSR consistently surpasses SOTA methods in both performance and noise robustness, highlighting the effectiveness of our model design.
title AD-AVSR: Asymmetric Dual-stream Enhancement for Robust Audio-Visual Speech Recognition
topic Multimedia
Computer Vision and Pattern Recognition
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2508.07608