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.
Towards controllable speech synthesis in the era of large language models: A systematic survey
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.