发表机构
Singapore Institute of Technology; Wuhan University; The Chinese University of Hong Kong; Duke Kunshan University（新加坡理工大学; 武汉大学; 香港中文大学; 昆山杜克大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对多语言语音匿名化，评估声学与内容导向的说话人验证攻击，发现声学攻击更有效，但语言信息保留时差距缩小，多语言数据集可提升性能并减少跨语言差距。
AI 中文摘要
针对语音匿名化的攻击者ASV系统主要是在英语环境下研究的，其在多语言环境中的行为在很大程度上尚未被探索。传统ASV研究表明，声学信息和上下文信息对于多语言说话人验证都至关重要。受此启发，我们研究了攻击者ASV在匿名化语音上是否也存在同样的现象。我们在多语言匿名化语音上评估了声学导向和内容导向的攻击者，并构建了一个多语言语音转换数据集以提高跨语言泛化能力。我们的结果表明，攻击者的有效性取决于匿名化语音的语言效用。总体而言，声学导向的攻击者取得了更好的性能。然而，当语言信息得到良好保留时，内容导向与声学导向攻击者之间的性能差距相比语音失真更强的情况有所缩小。多语言语音转换数据集进一步提高了性能，并部分减少了跨语言差距。这些发现强调需要更全面的攻击者建模和评估协议，同时考虑隐私和效用，而不是仅依赖单一的攻击者策略。完整代码、预训练模型和MultiVC数据集链接可在以下网址获取：this https URL
英文摘要
Attacker ASV systems for voice anonymization have been studied primarily in English, leaving their behavior in multilingual settings largely unexplored. Conventional ASV has shown that both acoustic and contextual information are important for multilingual speaker verification. Inspired by this, we investigate whether the same holds for attacker ASV on anonymized speech. We evaluate both acoustic- and content-oriented attackers on multilingual anonymized speech and construct a multilingual voice-converted dataset to improve cross-lingual generalization. Our results show that attacker effectiveness depends on the linguistic utility of the anonymized speech. Overall, acoustic-oriented attackers achieve better performance. However, when linguistic information is well preserved, the performance gap between content- and acoustic-oriented attackers narrows compared with conditions involving stronger speech distortion. The multilingual voice-converted dataset further improves performance and partially reduces the cross-lingual gap. These findings highlight the need for more comprehensive attacker modeling and evaluation protocols that consider both privacy and utility, rather than relying on a attacker strategy\footnote{Full code and pretrained models and MultiVC Dataset link are available at: https://github.com/monkeyDarefeen/DAST
CommentsAccepted in IEEE Spoken Language Technology (SLT) 2026
