Abstract
Attacker ASV systems for voice anonymization have been studied primarily in English, leaving their behavior in multilingual settings largely unexplored. Conventional ASV has shown that both acoustic and contextual information are important for multilingual speaker verification. Inspired by this, we investigate whether the same holds for attacker ASV on anonymized speech. We evaluate both acoustic- and content-oriented attackers on multilingual anonymized speech and construct a multilingual voice-converted dataset to improve cross-lingual generalization. Our results show that attacker effectiveness depends on the linguistic utility of the anonymized speech. Overall, acoustic-oriented attackers achieve better performance. However, when linguistic information is well preserved, the performance gap between content- and acoustic-oriented attackers narrows compared with conditions involving stronger speech distortion. The multilingual voice-converted dataset further improves performance and partially reduces the cross-lingual gap. These findings highlight the need for more comprehensive attacker modeling and evaluation protocols that consider both privacy and utility, rather than relying on a attacker strategy\footnote{Full code and pretrained models and MultiVC Dataset link are available at: https://github.com/monkeyDarefeen/DAST
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Arefeen, R., Li, Z., Tong, R., Li, M., & Miao, X. (2026). Exploiting Acoustic and Content-Oriented Speaker Verification Attacks Against Multilingual Voice Anonymization. https://omanscience.com/en/articles/exploiting-acoustic-and-content-oriented-speaker-verification-attacks-against-multilingual-voice-anonymization
MLA 9
Arefeen, Ridwan, et al. "Exploiting Acoustic and Content-Oriented Speaker Verification Attacks Against Multilingual Voice Anonymization." https://omanscience.com/en/articles/exploiting-acoustic-and-content-oriented-speaker-verification-attacks-against-multilingual-voice-anonymization.
Chicago (author–date)
Arefeen, Ridwan, Ze Li, Rong Tong, Ming Li, and Xiaoxiao Miao. 2026. "Exploiting Acoustic and Content-Oriented Speaker Verification Attacks Against Multilingual Voice Anonymization." https://omanscience.com/en/articles/exploiting-acoustic-and-content-oriented-speaker-verification-attacks-against-multilingual-voice-anonymization.
Harvard
Arefeen, R., Li, Z., Tong, R., Li, M. and Miao, X. (2026) 'Exploiting Acoustic and Content-Oriented Speaker Verification Attacks Against Multilingual Voice Anonymization', Available at: https://omanscience.com/en/articles/exploiting-acoustic-and-content-oriented-speaker-verification-attacks-against-multilingual-voice-anonymization.
Vancouver
Arefeen R, Li Z, Tong R, Li M, Miao X. Exploiting Acoustic and Content-Oriented Speaker Verification Attacks Against Multilingual Voice Anonymization. https://omanscience.com/en/articles/exploiting-acoustic-and-content-oriented-speaker-verification-attacks-against-multilingual-voice-anonymization
IEEE
R. Arefeen, Z. Li, R. Tong, M. Li, and X. Miao, "Exploiting Acoustic and Content-Oriented Speaker Verification Attacks Against Multilingual Voice Anonymization," https://omanscience.com/en/articles/exploiting-acoustic-and-content-oriented-speaker-verification-attacks-against-multilingual-voice-anonymization.