A two-stage framework replaces personally identifiable information via generative editing and anonymizes voices with a flow-matching model to achieve stronger privacy than VoicePrivacy baselines while keeping utility high for retrained ASR, TTS, and SER models.
The GDPR & speech data: Reflections of legal and tech- nology communities, first steps towards a common understanding,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Anonymization, Not Elimination: Utility-Preserved Speech Anonymization
A two-stage framework replaces personally identifiable information via generative editing and anonymizes voices with a flow-matching model to achieve stronger privacy than VoicePrivacy baselines while keeping utility high for retrained ASR, TTS, and SER models.