You Are What You Say: Exploiting Linguistic Content for VoicePrivacy Attacks

Gaznepoglu ÜE, Leschanowsky A, Aloradi A, Singh P, Tenbrinck D, Habets E, Peters N (2025)

Publication Type: Conference contribution

Publication year: 2025

Publisher: International Speech Communication Association

Pages Range: 4238-4242

Conference Proceedings Title: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Event location: Rotterdam, NLD

DOI: 10.21437/Interspeech.2025-681

Abstract

Speaker anonymization systems hide the identity of speakers while preserving other information such as linguistic content and emotions. To evaluate their privacy benefits, attacks in the form of automatic speaker verification (ASV) systems are employed. In this study, we assess the impact of intra-speaker linguistic content similarity in the attacker training and evaluation datasets, by adapting BERT, a language model, as an ASV system. On the VoicePrivacy Attacker Challenge datasets, our method achieves a mean equal error rate (EER) of 35%, with certain speakers attaining EERs as low as 2%, based solely on the textual content of their utterances. Our explainability study reveals that the system decisions are linked to semantically similar keywords within utterances, stemming from how LibriSpeech is curated. Our study suggests reworking the VoicePrivacy datasets to ensure a fair and unbiased evaluation and challenge the reliance on global EER for privacy evaluations.

Authors with CRIS profile

Involved external institutions

Fraunhofer-Institut für Integrierte Schaltungen (IIS) Germany (DE) Trinity College Dublin Ireland (IE)

How to cite

APA:

Gaznepoglu, Ü.E., Leschanowsky, A., Aloradi, A., Singh, P., Tenbrinck, D., Habets, E., & Peters, N. (2025). You Are What You Say: Exploiting Linguistic Content for VoicePrivacy Attacks. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (pp. 4238-4242). Rotterdam, NLD: International Speech Communication Association.

MLA:

Gaznepoglu, Ünal Ege, et al. "You Are What You Say: Exploiting Linguistic Content for VoicePrivacy Attacks." Proceedings of the 26th Interspeech Conference 2025, Rotterdam, NLD International Speech Communication Association, 2025. 4238-4242.

BibTeX: Download