Preprint
Aug 2026
Your Voice Cloning System is Secretly a Voice Anonymizer
Speaker anonymization suppresses speaker-identifying attributes from speech while preserving linguistic content and quality. We propose repurposing XTTSv2, a multilingual voice cloning model trained on 27k hours of speech, for speaker anonymization without retraining. Our key insight is that XTTSv2's voice cloning capa...
Romolo Muletta, Felix Matthias Saaro, Mark Cieliebak et al.
· 0 citations