A fine-tuning strategy with a pinhole loss for well-trained voice anonymization frameworks to further reduce residual speaker attributes in non-identity representations to improve privacy protection.
Abstract
Voice anonymization aims to protect privacy by suppressing speaker identity while preserving linguistic content and prosody. However, residual speaker attributes in non-identity representations may still increase linkability and weaken privacy protection. To this end, this paper proposes a fine-tuning strategy with a pinhole loss for well-trained voice anonymization frameworks to further reduce residual speaker attributes. Inspired by the pinhole effect, the pinhole loss measures the linkability of anonymized utterances from the same source speaker. By minimizing this loss, linkability is reduced, thereby improving privacy protection. Experiments on multiple anonymization frameworks, pseudo-speaker generation methods, and datasets show improved privacy protection while maintaining utility. Audio samples can be found in https://anonymous.4open.science/r/Pinhole-loss-fine-tunning-4628.
A training-free, two-stage anonymization method for pretrained flow-matching voice conversion systems that improves speaker privacy while maintaining competitive word error rate and emotion recognition performance.
This work proposes repurposing XTTSv2, a multilingual voice cloning model trained on 27k hours of speech, for speaker anonymization without retraining, and introduces an iterative refinement strategy that balances privacy and utility by maximizing a harmonic mean of speaker dissimilarity and intelligibility.
Romolo Muletta, Felix Matthias Saaro, Mark Cieliebak et al.· 0 citations
This work introduces speaker differential privacy, a formal definition of speaker anonymization based on the framework of differential privacy, and a mechanism for speaker anonymization that provably satisfies the definition.
Ivoline C. Ngong, Jack D'Iorio, Hailey Schoppe et al.· 0 citations
Speech anonymization is evaluated with automatic speaker verification attackers whose performance depends on the attribute distribution of both their training and evaluation data, which may bias privacy estimates for some speaker groups. To alleviate this issue, we introduce VoxAnon, a dataset built from VoxCeleb1 and...
Orane Dufour, Paul Magron, Mickael Rouvier· 0 citations
Voice anonymization (VA) is used to conceal the voice identities in speech data. Performance is usually estimated using automatic speaker verification (ASV) as a proxy to judge the capability of an attacker to re-identify speakers after anonymization. The defender anonymizes test utterances; the attacker compares them...
M. Panariello, Yi-Bo Bai, Massimiliano Todisco et al.· 0 citations
As the use of smart devices continues to increase, their potential to capture sensitive speech content raises growing privacy concerns. It is therefore critical to develop techniques that prevent information leakage while preserving the utility of the audio, and evaluation metrics that accurately quantify the level of...
A. Rajasekhar, Jule Pohlhausen, Nayana Jacob Alappattu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
