DP-VOXLET：用于解耦语音表示的可证明说话人匿名化
DP-VOXLET: Provable Speaker Anonymization for Disentangled Speech Representations
浏览论文内容
中文总结 AI 辅助
本研究提出基于差分隐私的说话人匿名化正式定义及可证明满足该定义的机制，在兼容现有解耦语音表示的框架下，相较此前方法实现了更高效用。
中文摘要 AI 辅助
说话人匿名化系统会混淆话语的说话人身份，同时保留其原始语义内容和韵律。近期的说话人匿名化解决方案依赖于将话语解耦为语义内容和说话人属性的学习表示，这类系统通过替换说话人属性、保留语义内容来实现匿名化，在隐私的经验度量上可产生良好效果。本研究中，我们引入基于差分隐私框架的说话人匿名化正式定义——说话人差分隐私，以及可证明满足该定义的说话人匿名化机制。与此前基于启发式的匿名化系统不同，我们的方法可为任何可能的攻击者提供可证明的重识别成功率（如等错误率）下界。我们在兼容现有解耦表示的框架中实现了该方法，与此前的说话人匿名化差分隐私研究相比，我们的方法实现了显著更高的效用。
英文摘要
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.
