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 capabilities preserve prosodic structure independently of speaker identity, enabling voice conversion by conditioning on a pseudo-speaker. We introduce an iterative refinement strategy that balances privacy and utility by maximizing a harmonic mean of speaker dissimilarity and intell
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 58%Best AI Voice Cloning in 2026: How to Clone Your Voice With AI →
- PossiblePossibly related (embedding) · 53%Launch HN: Speko (YC S26) – OpenRouter for Voice AI →
- PossiblePossibly related (embedding) · 48%Matt Lucas and Hugh Bonneville among actors calling for law on AI voice cloning →
- LinkedLinked via arxiv author · 85%Romolo Muletta →
“Your Voice Cloning System is Secretly a Voice Anonymizer”
- LinkedLinked via arxiv author · 85%Felix Matthias Saaro →
“Your Voice Cloning System is Secretly a Voice Anonymizer”
- LinkedLinked via arxiv author · 85%Mark Cieliebak →
“Your Voice Cloning System is Secretly a Voice Anonymizer”
- LinkedLinked via arxiv author · 85%Jan Deriu →
“Your Voice Cloning System is Secretly a Voice Anonymizer”