AI RESEARCH

DiffAnon: Diffusion-based Prosody Control for Voice Anonymization

arXiv CS.LG

ArXi:2604.26281v1 Announce Type: cross To preserve or not to preserve prosody is a central question in voice anonymization. Prosody conveys meaning and affect, yet is tightly coupled with speaker identity. Existing methods either discard prosody for privacy or lack a principled mechanism to control the utility-privacy trade-off, operating at fixed design points. We propose DiffAnon, a diffusion-based anonymization method with classifier-free guidance (CFG) that provides explicit, continuous inference-time control over prosody preservation.