Redirecting to original paper in 30 seconds...

Click below to go immediately or wait for automatic redirect

arxiv_cv 95% Match Research Paper Speech processing researchers,Audio engineers,Developers of voice-enabled systems,Audiologists 2 days ago

Audio-Visual Speech Enhancement In Complex Scenarios With Separation And Dereverberation Joint Modeling

speech-audio › multimodal-audio
📄 Abstract

Abstract: Audio-visual speech enhancement (AVSE) is a task that uses visual auxiliary information to extract a target speaker's speech from mixed audio. In real-world scenarios, there often exist complex acoustic environments, accompanied by various interfering sounds and reverberation. Most previous methods struggle to cope with such complex conditions, resulting in poor perceptual quality of the extracted speech. In this paper, we propose an effective AVSE system that performs well in complex acoustic environments. Specifically, we design a "separation before dereverberation" pipeline that can be extended to other AVSE networks. The 4th COGMHEAR Audio-Visual Speech Enhancement Challenge (AVSEC) aims to explore new approaches to speech processing in multimodal complex environments. We validated the performance of our system in AVSEC-4: we achieved excellent results in the three objective metrics on the competition leaderboard, and ultimately secured first place in the human subjective listening test.
Authors (7)
Jiarong Du
Zhan Jin
Peijun Yang
Juan Liu
Zhuo Li
Xin Liu
+1 more
Submitted
October 29, 2025
arXiv Category
cs.SD
arXiv PDF

Key Contributions

This paper proposes an effective Audio-Visual Speech Enhancement (AVSE) system that excels in complex acoustic environments by employing a novel 'separation before dereverberation' pipeline. This approach, validated in the AVSEC-4 challenge, significantly improves speech quality and intelligibility, achieving first place in human subjective evaluations.

Business Value

Improved speech clarity in noisy environments is crucial for applications like voice assistants, teleconferencing, and hearing aids, enhancing user experience and accessibility.