Score: 1

Incorporating Linguistic Constraints from External Knowledge Source for Audio-Visual Target Speech Extraction

Published: June 11, 2025 | arXiv ID: 2506.09792v2

By: Wenxuan Wu , Shuai Wang , Xixin Wu and more

Potential Business Impact:

Helps computers hear one voice in noisy rooms.

Business Areas:
Semantic Search Internet Services

Audio-visual target speaker extraction (AV-TSE) models primarily rely on target visual cues to isolate the target speaker's voice from others. We know that humans leverage linguistic knowledge, such as syntax and semantics, to support speech perception. Inspired by this, we explore the potential of pre-trained speech-language models (PSLMs) and pre-trained language models (PLMs) as auxiliary knowledge sources for AV-TSE. In this study, we propose incorporating the linguistic constraints from PSLMs or PLMs for the AV-TSE model as additional supervision signals. Without introducing any extra computational cost during inference, the proposed approach consistently improves speech quality and intelligibility. Furthermore, we evaluate our method in multi-language settings and visual cue-impaired scenarios and show robust performance gains.

Country of Origin
🇨🇳 🇭🇰 China, Hong Kong

Page Count
5 pages

Category
Computer Science:
Sound