A context-dependent encoding of phoneme durations identifies speakers far better than average-duration vectors and remains effective on anonymized speech without retraining on anonymized data.
Exploiting Context-dependent Duration Features for Voice Anonymization Attack Systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exploiting Context-dependent Duration Features for Voice Anonymization Attack Systems
A context-dependent encoding of phoneme durations identifies speakers far better than average-duration vectors and remains effective on anonymized speech without retraining on anonymized data.