← Back to all news
arXiv Computation and Language By Romolo Muletta, Felix Matthias Saaro, Mark Cieliebak, Jan Deriu

Your Voice Cloning System is Secretly a Voice Anonymizer

Read the original on arXiv Computation and Language →

The paper demonstrates that the multilingual voice cloning model XTTSv2 can be repurposed for speaker anonymization without retraining. By conditioning on a pseudo-speaker and using an iterative refinement strategy, the authors balance privacy and intelligibility, achieving near‑optimal privacy (EER ≈ 0.49) and competitive speech quality across seven European languages. The method outperforms dedicated anonymization baselines and requires no language‑specific training.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
Oct 7

Voice "Cloning" is Style Transfer

arXiv:2605.16578v4 Announce Type: replace-cross Abstract: Artificially generated speech is increasingly embedded in everyday life. Voice cloning in particular enables applications where identity pres...

By Kaitlyn Zhou, Federico Bianchi, Martijn Bartelds, Anna Pot, Yongchan Kwon, James Zou
rag
More like this →
arXiv AI
Sep 4

Anonymization, Not Elimination: Utility-Preserved Speech Anonymization

The paper introduces a two‑stage speech anonymization framework that preserves both linguistic content and acoustic identity. It replaces personally identifiable information using a generative editing model and applies a flow‑matching anonymization technique (F3‑VA) to create diverse, distinct anonymized speakers. The authors evaluate privacy with speaker verification metrics and utility by training ASR, TTS, and SER models from scratch, showing stronger privacy protection with minimal utility loss compared to existing baselines.

By Yunchong Xiao, Yuxiang Zhao, Ziyang Ma, Shuai Wang, Kai Yu, Jiachun Liao, Xie Chen
multimodalsafety
More like this →
arXiv Machine Learning
Sep 24

PHONOS: PHOnetic Neutralization for Online Streaming Applications

PHONOS is a real‑time streaming module for speaker anonymization that neutralizes accent cues by converting non‑native segmental realizations toward a target accent domain. It uses pre‑generated golden utterances that preserve timbre and rhythm, aligning them with silence‑aware DTW and applying zero‑shot voice conversion to supervise a causal accent translator. The system achieves an 81% reduction in non‑native accent confidence, improves accentedness ratings, reduces speaker linkability in embedding space, and operates with ≤241 ms end‑to‑end latency on a single GPU.

By Waris Quamer, Mu-Ruei Tseng, Ghady Nasrallah, Ricardo Gutierrez-Osuna
ragsafety
More like this →
arXiv AI
Jul 14

Listen to the Features: Voice Anonymization Driven by Content Embedding Matching over Signal Reconstruction

arXiv:2607. 09767v1 Announce Type: cross Abstract: The paper presents a voice anonymization model focusing on preserving content rather than producing realistic speech.

By Adrien Schneider (M-PSI), Kacper Zabkowski (M-PSI), Anderson Augusma (M-PSI), Fr\'ed\'erique Letu\'e (SAM, SVH), Maria Camila Pinzon (M-PSI), Dominique Vaufreydaz (M-PSI)
ragdiffusionefficiency
More like this →