Voice privacy approaches that preserve the anonymity of speakers modify speech in an attempt to break the link with the true identity of the speaker. Current benchmarks measure speaker protection based on signal-to-signal comparisons. In this paper, we introduce an attribute-based perspective, where we measure privacy protection in terms of comparisons between sets of speaker attributes. First, we analyze privacy impact by calculating speaker uniqueness for ground truth attributes, attributes inferred on the original speech, and attributes inferred on speech protected with standard anonymization. Next, we examine a threat scenario involving only a single utterance per speaker and calculate attack error rates. Overall, we observe that inferred attributes still present a risk despite attribute inference errors. Our research points to the importance of considering both attribute-related threats and protection mechanisms in future voice privacy research.

翻译：从属性角度出发的语音隐私方法通过修改语音，试图切断与说话者真实身份的联系，以保护说话者的匿名性。当前的基准测试基于信号间比较来衡量说话者保护程度。本文引入基于属性的视角，通过说话者属性集合间的比较来衡量隐私保护水平。首先，我们通过计算真值属性、从原始语音推断出的属性以及经标准匿名化保护后语音推断出的属性的说话者独特性，分析隐私影响。接着，我们考察了每个说话者仅涉及单个话语的威胁场景，并计算攻击错误率。总体而言，我们观察到即使存在属性推断错误，推断出的属性仍构成风险。我们的研究指出了在未来语音隐私研究中同时考虑属性相关威胁与保护机制的重要性。