CoGenAV: Versatile Audio-Visual Representation Learning via Contrastive-Generative Synchronization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bai, Detao, Ma, Zhiheng, Wei, Xihan, Bo, Liefeng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915287699292160
author Bai, Detao
Ma, Zhiheng
Wei, Xihan
Bo, Liefeng
author_facet Bai, Detao
Ma, Zhiheng
Wei, Xihan
Bo, Liefeng
contents The inherent synchronization between a speaker's lip movements, voice, and the underlying linguistic content offers a rich source of information for improving speech processing tasks, especially in challenging conditions where traditional audio-only systems falter. We introduce CoGenAV, a powerful and data-efficient model designed to learn versatile audio-visual representations applicable across a wide range of speech and audio-visual tasks. CoGenAV is trained by optimizing a dual objective derived from natural audio-visual synchrony, contrastive feature alignment and generative text prediction, using only 223 hours of labeled data from the LRS2 dataset. This contrastive-generative synchronization strategy effectively captures fundamental cross-modal correlations. We showcase the effectiveness and versatility of the learned CoGenAV representations on multiple benchmarks. When utilized for Audio-Visual Speech Recognition (AVSR) on LRS2, these representations contribute to achieving a state-of-the-art Word Error Rate (WER) of 1.27. They also enable strong performance in Visual Speech Recognition (VSR) with a WER of 20.5 on LRS2, and significantly improve performance in noisy environments by over 70%. Furthermore, CoGenAV representations benefit speech reconstruction tasks, boosting performance in Speech Enhancement and Separation, and achieve competitive results in audio-visual synchronization tasks like Active Speaker Detection (ASD). Our model will be open-sourced to facilitate further development and collaboration within both academia and industry.
format Preprint
id arxiv_https___arxiv_org_abs_2505_03186
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CoGenAV: Versatile Audio-Visual Representation Learning via Contrastive-Generative Synchronization
Bai, Detao
Ma, Zhiheng
Wei, Xihan
Bo, Liefeng
Sound
Computer Vision and Pattern Recognition
Audio and Speech Processing
The inherent synchronization between a speaker's lip movements, voice, and the underlying linguistic content offers a rich source of information for improving speech processing tasks, especially in challenging conditions where traditional audio-only systems falter. We introduce CoGenAV, a powerful and data-efficient model designed to learn versatile audio-visual representations applicable across a wide range of speech and audio-visual tasks. CoGenAV is trained by optimizing a dual objective derived from natural audio-visual synchrony, contrastive feature alignment and generative text prediction, using only 223 hours of labeled data from the LRS2 dataset. This contrastive-generative synchronization strategy effectively captures fundamental cross-modal correlations. We showcase the effectiveness and versatility of the learned CoGenAV representations on multiple benchmarks. When utilized for Audio-Visual Speech Recognition (AVSR) on LRS2, these representations contribute to achieving a state-of-the-art Word Error Rate (WER) of 1.27. They also enable strong performance in Visual Speech Recognition (VSR) with a WER of 20.5 on LRS2, and significantly improve performance in noisy environments by over 70%. Furthermore, CoGenAV representations benefit speech reconstruction tasks, boosting performance in Speech Enhancement and Separation, and achieve competitive results in audio-visual synchronization tasks like Active Speaker Detection (ASD). Our model will be open-sourced to facilitate further development and collaboration within both academia and industry.
title CoGenAV: Versatile Audio-Visual Representation Learning via Contrastive-Generative Synchronization
topic Sound
Computer Vision and Pattern Recognition
Audio and Speech Processing
url https://arxiv.org/abs/2505.03186