Volker Dellwo

Unified Shared Encoder in Spoof-Aware Speaker Verification with Hybrid Wavelet Prompt Tuning

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 ha...