Metraipolis › archive › dc_01ab69a8fc5d
Unified Shared Encoder in Spoof-Aware Speaker Verification with Hybrid Wavelet Prompt Tuning — arXiv:2610.08845
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.08845
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T14:17:22.597Z
- SHA-256 of the archived text
200c918ef5e4c2975f2cd82313bedf3de51915665f4ba7abf84e55fa6905e018- Stable URL of this page
https://metraipolis.com/documento/dc_01ab69a8fc5d
How to cite
Unified Shared Encoder in Spoof-Aware Speaker Verification with Hybrid Wavelet Prompt Tuning — arXiv:2610.08845 — arXiv (en), https://arxiv.org/abs/2610.08845 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_01ab69a8fc5d (Metraipolis archive dc_01ab69a8fc5d, sha256 200c918ef5e4c2975f2cd82313bedf3de51915665f4ba7abf84e55fa6905e018)
BibTeX
@misc{dc01ab69a8fc5d,
title = {Unified Shared Encoder in Spoof-Aware Speaker Verification with Hybrid Wavelet Prompt Tuning — arXiv:2610.08845},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.08845},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_01ab69a8fc5d; sha256 200c918ef5e4c2975f2cd82313bedf3de51915665f4ba7abf84e55fa6905e018},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08845. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Spoofing-aware speaker verification (SASV) must confirm who is speaking and that the speech is genuine, but current systems gain one at the expense of the other. Modular cascades are accurate yet run two large self-supervised encoders, whereas end-to-end models are efficient but lose accuracy when a single embedding has to serve two conflicting objectives. We show that this trade-off between efficiency and specialization is avoidable. A single frozen W2V-BERT~2.0 backbone is adapted per task by deep hybrid Wavelet Prompt Tuning (WPT), so each branch obtains its own view of the shared encoder through dedicated prompts and a task head, and the scores are combined only at inference. Training only about 7M parameters, a small fraction of those a strong two-encoder cascade requires, the system surpasses it on SpoofCeleb evaluation with 0.03% CM-EER and 0.038 min a-DCF against 0.16% and 0.047. Because the backbone is shared and frozen, new branches attach without retraining the heads and prompts already in place. On ASVspoof5, with adversarial attacks and codec distortions, it reaches 0.092 min a-DCF and 3.60% CM-EER using only the provided data, indicating that the design holds under realistic in-the-wild threats. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv eess.AS, nuovi lavori del giorno). Categorie arXiv: Audio and Speech Processing (eess.AS) ; Sound (cs.SD). Pagina del lavoro: https://arxiv.org/abs/2610.08845 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T13:29:00.749Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).