The VoicePrivacy 2022 Challenge: Progress and Perspectives in Voice Anonymisation

TL;DR

The VoicePrivacy 2022 Challenge evaluates voice anonymisation methods, revealing trade-offs between privacy and utility, with voice conversion and hybrid approaches showing promising results.

Contribution

This paper provides a comprehensive overview and analysis of the second VoicePrivacy Challenge, including datasets, attack models, evaluation metrics, and system performances.

Findings

Voice conversion methods better preserve utility.

Hybrid approaches combining ASR and synthesis enhance privacy.

A fundamental privacy-utility trade-off persists in current solutions.

Abstract

The VoicePrivacy Challenge promotes the development of voice anonymisation solutions for speech technology. In this paper we present a systematic overview and analysis of the second edition held in 2022. We describe the voice anonymisation task and datasets used for system development and evaluation, present the different attack models used for evaluation, and the associated objective and subjective metrics. We describe three anonymisation baselines, provide a summary description of the anonymisation systems developed by challenge participants, and report objective and subjective evaluation results for all. In addition, we describe post-evaluation analyses and a summary of related work reported in the open literature. Results show that solutions based on voice conversion better preserve utility, that an alternative which combines automatic speech recognition with synthesis achieves greater privacy, and that a privacy-utility trade-off remains inherent to current anonymisation solutions. Finally, we present our ideas and priorities for future VoicePrivacy Challenge editions.