评估说话人去识别系统中的身份泄露
Evaluating Identity Leakage in Speaker De-Identification Systems
- National Institute of Standards and Technology（国家标准与技术研究院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对说话人去识别系统的身份泄露问题，本文引入含三种互补错误率的基准量化残余泄露，发现所有最先进系统均存在泄露，性能最佳者仅略优于随机猜测，最差者Top50命中率达45%，凸显现有技术隐私风险。
AI中文摘要：
说话人去识别旨在隐藏说话人身份的同时保留底层语音的可懂度。我们引入一个基准，通过三种互补的错误率量化残余身份泄露：等错误率、累积匹配特征命中率，以及通过典型相关分析和普罗克拉斯提斯分析测量的嵌入空间相似度。评估结果显示，所有最先进的说话人去识别系统均存在身份信息泄露。我们评估中性能最佳的系统仅略优于随机猜测，而性能最差的系统基于CMC在Top 50候选者中达到45%的命中率。这些发现凸显了当前说话人去识别技术中持续存在的隐私风险。
英文摘要：
Speaker de-identification aims to conceal a speaker's identity while preserving intelligibility of the underlying speech. We introduce a benchmark that quantifies residual identity leakage with three complementary error rates: equal error rate, cumulative match characteristic hit rate, and embedding-space similarity measured via canonical correlation analysis and Procrustes analysis. Evaluation results reveal that all state-of-the-art speaker de-identification systems leak identity information. The highest performing system in our evaluation performs only slightly better than random guessing, while the lowest performing system achieves a 45% hit rate within the top 50 candidates based on CMC. These findings highlight persistent privacy risks in current speaker de-identification technologies.
