VOSSA: Voiceprint Optimization for Streaming Speech Architectures
Real-time voice conversion (VC) systems commonly rely on pretrained speaker embeddings from automatic speaker verification (ASV) models. While effective for speaker discrimination, these embeddings are trained to remain stable across phonetic and prosodic variations within-speaker, which may conflict with frame-level a...
Mu-Ruei Tseng, Waris Quamer, Ghady Nasrallah et al.
· 0 citations