Attacking Voice Anonymization Systems with Augmented Feature and Speaker Identity Difference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yanzhe, Bi, Zhonghao, Xiao, Feiyang, Yang, Xuefeng, Zhu, Qiaoxi, Guan, Jian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913643957846016
author Zhang, Yanzhe
Bi, Zhonghao
Xiao, Feiyang
Yang, Xuefeng
Zhu, Qiaoxi
Guan, Jian
author_facet Zhang, Yanzhe
Bi, Zhonghao
Xiao, Feiyang
Yang, Xuefeng
Zhu, Qiaoxi
Guan, Jian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19068
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Attacking Voice Anonymization Systems with Augmented Feature and Speaker Identity Difference
Zhang, Yanzhe
Bi, Zhonghao
Xiao, Feiyang
Yang, Xuefeng
Zhu, Qiaoxi
Guan, Jian
Audio and Speech Processing
Sound
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.
title Attacking Voice Anonymization Systems with Augmented Feature and Speaker Identity Difference
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2412.19068