AI RESEARCH

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

arXiv CS.CL

ArXi:2506.09521v2 Announce Type: replace-cross 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