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.
This model is expected to be robust to modifications of the speech signal during anonymization other than changes in the temporal dynamics
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
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.