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

June 11, 2025 ยท Declared Dead ยท ๐Ÿ› Interspeech

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Wenxuan Wu, Shuai Wang, Xixin Wu, Helen Meng, Haizhou Li arXiv ID 2506.09792 Category cs.SD: Sound Cross-listed cs.LG, cs.MM, eess.AS Citations 2 Venue Interspeech Last Checked 4 months ago
Abstract
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Sound

Died the same way โ€” ๐Ÿ‘ป Ghosted