|国家预印本平台
首页|Incorporating Linguistic Constraints from External Knowledge Source for Audio-Visual Target Speech Extraction

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

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

来源:Arxiv_logoArxiv
英文摘要

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.

Wenxuan Wu、Shuai Wang、Xixin Wu、Helen Meng、Haizhou Li

语言学

Wenxuan Wu,Shuai Wang,Xixin Wu,Helen Meng,Haizhou Li.Incorporating Linguistic Constraints from External Knowledge Source for Audio-Visual Target Speech Extraction[EB/OL].(2025-06-11)[2025-07-16].https://arxiv.org/abs/2506.09792.点此复制

评论