Exploiting Context-dependent Duration Features for Voice Anonymization Attack Systems
This work addresses security risks in voice-based systems for users and developers, but it is incremental as it builds on existing representations of speech temporal dynamics.
The paper tackled the problem of speaker verification and voice anonymization vulnerabilities by proposing a new method for extracting context-dependent duration embeddings from speech temporal dynamics, resulting in attack models that significantly improved speaker verification performance on both original and anonymized data compared to simpler representations.
The temporal dynamics of speech, encompassing variations in rhythm, intonation, and speaking rate, contain important and unique information about speaker identity. This paper proposes a new method for representing speaker characteristics by extracting context-dependent duration embeddings from speech temporal dynamics. We develop novel attack models using these representations and analyze the potential vulnerabilities in speaker verification and voice anonymization systems.The experimental results show that the developed attack models provide a significant improvement in speaker verification performance for both original and anonymized data in comparison with simpler representations of speech temporal dynamics reported in the literature.