DAST：一种双流语音匿名攻击者与分阶段训练
DAST: A Dual-Stream Voice Anonymization Attacker with Staged Training
AI总结：
本文提出一种双流攻击者，通过并行编码器融合频谱和自监督学习特征，分三阶段训练以提升隐私评估效果，实验表明第二阶段是提升泛化能力的关键，仅用10%的目标数据微调即可超越现有最佳攻击者。
摘要：
语音匿名化在掩盖语音特征的同时保留语言内容，可能仍泄露说话者特定模式。为评估和加强隐私评估，我们提出一种双流攻击者，通过并行编码器融合频谱和自监督学习特征，并采用三阶段训练策略。第一阶段建立基础的说话人判别表示。第二阶段利用语音转换和匿名化共享的身份转换特性，使模型暴露于多种转换语音以构建跨系统鲁棒性。第三阶段提供轻量级适应以针对匿名数据。在VoicePrivacy Attacker Challenge (VPAC)数据集上的结果表明，第二阶段是泛化能力的主要驱动因素，使攻击者在未见匿名数据集上表现强劲。借助第三阶段，仅在目标匿名数据集的10%上微调即可在EER方面超越现有最佳攻击者。
英文摘要：
Voice anonymization masks vocal traits while preserving linguistic content, which may still leak speaker-specific patterns. To assess and strengthen privacy evaluation, we propose a dual-stream attacker that fuses spectral and self-supervised learning features via parallel encoders with a three-stage training strategy. Stage I establishes foundational speaker-discriminative representations. Stage II leverages the shared identity-transformation characteristics of voice conversion and anonymization, exposing the model to diverse converted speech to build cross-system robustness. Stage III provides lightweight adaptation to target anonymized data. Results on the VoicePrivacy Attacker Challenge (VPAC) dataset demonstrate that Stage II is the primary driver of generalization, enabling strong attacking performance on unseen anonymization datasets. With Stage III, fine-tuning on only 10\% of the target anonymization dataset surpasses current state-of-the-art attackers in terms of EER.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
