mlsanityData to 14 Oct 2026

Your Voice Cloning System is Secretly a Voice Anonymizer

arXiv 2608.27360 ↗First posted 27 Aug 2026cs.CLcited by 0

Not on the map. Why?

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.

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

20 of 28 references.

References · 20

  1. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  3. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  4. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  5. 2020MLS: A Large-Scale Multilingual Dataset for Speech Researchcited by 476
  6. 2022UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022cited by 390
  7. 2024XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Modelcited by 179
  8. 2023Better speech synthesis through scalingcited by 63
  9. 2020Introducing the VoicePrivacy Initiativecited by 49
  10. 2024The VoicePrivacy 2024 Challenge Evaluation Plancited by 41
  11. 2020Speaker anonymisation using the McAdams coefficientcited by 38
  12. 2020Clova Baseline System for the VoxCeleb Speaker Recognition Challenge 2020cited by 36
8 more
  1. 2023Speaker anonymization using neural audio codec language modelscited by 22
  2. 2024ECAPA2: A Hybrid Neural Network Architecture and Training Strategy for Robust Speaker Embeddingscited by 22
  3. 2022Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacycited by 21
  4. 2024The VoicePrivacy 2022 Challenge: Progress and Perspectives in Voice Anonymisationcited by 17
  5. 2022Language-Independent Speaker Anonymization Approach using Self-Supervised Pre-Trained Modelscited by 14
  6. 2022Analyzing Language-Independent Speaker Anonymization Framework under Unseen Conditionscited by 6
  7. 2024Probing the Feasibility of Multilingual Speaker Anonymizationcited by 5
  8. 2023SALT: Distinguishable Speaker Anonymization Through Latent Space Transformationcited by 1

Built on by

Not cited yet.