SpecWav-Attack: Leveraging Spectrogram Resizing and Wav2Vec 2.0 for Attacking Anonymized Speech
Sound
2025-05-16 v1 Artificial Intelligence
Audio and Speech Processing
Abstract
This paper presents SpecWav-Attack, an adversarial model for detecting speakers in anonymized speech. It leverages Wav2Vec2 for feature extraction and incorporates spectrogram resizing and incremental training for improved performance. Evaluated on librispeech-dev and librispeech-test, SpecWav-Attack outperforms conventional attacks, revealing vulnerabilities in anonymized speech systems and emphasizing the need for stronger defenses, benchmarked against the ICASSP 2025 Attacker Challenge.
Keywords
Cite
@article{arxiv.2505.09616,
title = {SpecWav-Attack: Leveraging Spectrogram Resizing and Wav2Vec 2.0 for Attacking Anonymized Speech},
author = {Yuqi Li and Yuanzhong Zheng and Zhongtian Guo and Yaoxuan Wang and Jianjun Yin and Haojun Fei},
journal= {arXiv preprint arXiv:2505.09616},
year = {2025}
}
Comments
2 pages,3 figures,1 chart