Attacking Voice Anonymization Systems with Augmented Feature and Speaker Identity Difference
Abstract
This study focuses on the First VoicePrivacy Attacker Challenge within the ICASSP 2025 Signal Processing Grand Challenge, which aims to develop speaker verification systems capable of determining whether two anonymized speech signals are from the same speaker. However, differences between feature distributions of original and anonymized speech complicate this task. To address this challenge, we propose an attacker system that combines Data Augmentation enhanced feature representation and Speaker Identity Difference enhanced classifier to improve verification performance, termed DA-SID. Specifically, data augmentation strategies (i.e., data fusion and SpecAugment) are utilized to mitigate feature distribution gaps, while probabilistic linear discriminant analysis (PLDA) is employed to further enhance speaker identity difference. Our system significantly outperforms the baseline, demonstrating exceptional effectiveness and robustness against various voice anonymization systems, ultimately securing a top-5 ranking in the challenge.
Keywords
Cite
@article{arxiv.2412.19068,
title = {Attacking Voice Anonymization Systems with Augmented Feature and Speaker Identity Difference},
author = {Yanzhe Zhang and Zhonghao Bi and Feiyang Xiao and Xuefeng Yang and Qiaoxi Zhu and Jian Guan},
journal= {arXiv preprint arXiv:2412.19068},
year = {2025}
}
Comments
2 pages, submitted to ICASSP 2025 GC-7: The First VoicePrivacy Attacker Challenge (by invitation), fixed a numerical typo: In Table II, the EER% for DA-SID w/o DA under T8-5 is corrected to 26.96