Your Voice Cloning System is Secretly a Voice Anonymizer
Romolo Muletta, Felix Matthias Saaro, Mark Cieliebak, Jan Deriu
Abstract
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 intelligibility. Evaluated on seven European languages across CommonVoice and Multilingual LibriSpeech, our system achieves near-optimal privacy (EER ≈ 0.49), competitive intelligibility, and substantially better speech quality than dedicated anonymization baselines, while requiring no language-specific training. We release the code here: https://github.com/rm00cr/coqui-tts.
Create a lesson
Related papers
CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes
Yufan Wu, Yinghui He, Zhengyi Hu et al.
TTPO: Test-Time Policy Optimization
Aozhe Wang, Zhengxi Lu, Jianze Wang et al.
Stochastic Estimation of Transduced Language Models
Vésteinn Snæbjarnarson, Samuel Kiegeland, Manuel de Prada Corral et al.
Boosting LLM Exploration via Weak-Model Guidance in RLVR
Xingyu Shen, Huishuai Zhang, Peng Li et al.
Consolidating RLVR Capabilities Across Domains: A Deep Dive into Fusion Paradigms
Siye Wu, Kai Yang, Yuchen Cai et al.
How Language Models Organize and Structure Moral Knowledge
Orion Reblitz-Richardson