# Your Voice Cloning System is Secretly a Voice Anonymizer

arXiv: https://arxiv.org/abs/2608.27360 · HTML: https://mlsanity.com/paper/2608.27360/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 27 Aug 2026.

## Builds on (most cited first, 20 of 20)

- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model](https://mlsanity.com/paper/2406.04904/) (2024)
- [Better speech synthesis through scaling](https://mlsanity.com/paper/2305.07243/) (2023)
- [Introducing the VoicePrivacy Initiative](https://mlsanity.com/paper/2005.01387/) (2020)
- [The VoicePrivacy 2024 Challenge Evaluation Plan](https://mlsanity.com/paper/2404.02677/) (2024)
- [Speaker anonymisation using the McAdams coefficient](https://mlsanity.com/paper/2011.01130/) (2020)
- [Clova Baseline System for the VoxCeleb Speaker Recognition Challenge 2020](https://mlsanity.com/paper/2009.14153/) (2020)
- [Speaker anonymization using neural audio codec language models](https://mlsanity.com/paper/2309.14129/) (2023)
- [ECAPA2: A Hybrid Neural Network Architecture and Training Strategy for Robust Speaker Embeddings](https://mlsanity.com/paper/2401.08342/) (2024)
- [Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacy](https://mlsanity.com/paper/2210.07002/) (2022)
- [The VoicePrivacy 2022 Challenge: Progress and Perspectives in Voice Anonymisation](https://mlsanity.com/paper/2407.11516/) (2024)
- [Language-Independent Speaker Anonymization Approach using Self-Supervised Pre-Trained Models](https://mlsanity.com/paper/2202.13097/) (2022)
- [Analyzing Language-Independent Speaker Anonymization Framework under Unseen Conditions](https://mlsanity.com/paper/2203.14834/) (2022)
- [Probing the Feasibility of Multilingual Speaker Anonymization](https://mlsanity.com/paper/2407.02937/) (2024)
- [SALT: Distinguishable Speaker Anonymization Through Latent Space Transformation](https://mlsanity.com/paper/2310.05051/) (2023)

## Abstract (arXiv)

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.