Papers › Wanna hear your voice? A sample is all we need!
Wanna hear your voice? A sample is all we need!
The Hieu Pham, Phuong Thanh Tran Nguyen, Xuan Tho Nguyen, Tan Dat Nguyen, Duc Dung Nguyen
Research on audio clue-based target speaker extraction (TSE) has focused on modeling mixtures and reference speech, achieving strong results in English due to abundant datasets. However, cross-lingual properties remain underexplored, as low-resource languages face challenges from limited annotated data and linguistic resources. To bridge this gap, we propose WHYV (Wanna Hear Your Voice), a cross-lingual TSE framework enabling zero-shot adaptation without fine-tuning. WHYV employs a frequency-modulated gating mechanism that dynamically adjusts the acoustic features of the target speaker, minimizing reliance on language-specific cues. Evaluations demonstrate state-of-the-art zero-shot performance: 13.8 dB (Libri2Mix mix-both), 18.1 dB (mix-clean), and 14.8 dB on Vietnamese data.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Speech Separation | Libri2Mix | WHYV | SDR | 17.2458 | #5 of 10 | Archive leaderboard | report |
| Speech Separation | Libri2Mix | WHYV | SI-SDRi | 17.5 | #5 of 10 | Archive leaderboard | report |
| Speech Separation | WHAM! | WHYV | SI-SDRi | 12.964 | #6 of 6 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections