DP-VOXLET: Provable Speaker Anonymization for Disentangled Speech Representations

2026-08-31

AI Summary

本文提出了一种基于差分隐私的说话人匿名化方法DP-VOXLET，用于在保持语义内容不变的同时，为解缠语音表示提供可证明的说话人隐私保护。

Abstract

Systems for speaker anonymization obfuscate the speaker of an utterance, while maintaining its original semantic contents and prosody. Recent solutions for speaker anonymization rely on learned representations that disentangle an utterance into semantic contents and speaker properties. To anonymize an utterance, these systems replace the speaker properties while leaving the semantic contents unchanged---an approach that can produce strong results on empirical measures of privacy. In this work, we introduce 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. In contrast to prior heuristic-based anonymization systems, our approach enables a provable lower bound on re-identification success rate (e.g. equal error rate) for any possible adversary. We implement our approach in a framework that is compatible with existing disentangled representations. Compared to the prior work on differential privacy for speaker anonymization, our approach achieves significantly higher utility.

Problem

• speaker anonymization
• disentangled speech representations
• differential privacy

Innovation

• speaker anonymization
• differential privacy
• disentangled representations