#artificial intelligence
Apr 2026
Anonymization, Not Elimination: Utility-Preserved Speech Anonymization
This work proposes a novel two-stage framework that protects both linguistic content and acoustic identity while maintaining usability and introduces F3-VA, a flow-matching-based anonymization framework with a three-stage design that produces diverse and distinct anonymized speakers.
Yunchong Xiao, Yuxiang Zhao, Ziyang Ma et al.
· IEEE Transactions on Audio,... · 1 citation