SpecWav-Attack: Leveraging Spectrogram Resizing and Wav2Vec 2.0 for Attacking Anonymized Speech
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915287787372544 |
|---|---|
| author | Li, Yuqi Zheng, Yuanzhong Guo, Zhongtian Wang, Yaoxuan Yin, Jianjun Fei, Haojun |
| author_facet | Li, Yuqi Zheng, Yuanzhong Guo, Zhongtian Wang, Yaoxuan Yin, Jianjun Fei, Haojun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_09616 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SpecWav-Attack: Leveraging Spectrogram Resizing and Wav2Vec 2.0 for Attacking Anonymized Speech Li, Yuqi Zheng, Yuanzhong Guo, Zhongtian Wang, Yaoxuan Yin, Jianjun Fei, Haojun Sound Artificial Intelligence Audio and Speech Processing I.2.0 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. |
| title | SpecWav-Attack: Leveraging Spectrogram Resizing and Wav2Vec 2.0 for Attacking Anonymized Speech |
| topic | Sound Artificial Intelligence Audio and Speech Processing I.2.0 |
| url | https://arxiv.org/abs/2505.09616 |