AI RESEARCH
DAST: A Dual-Stream Voice Anonymization Attacker with Staged Training
arXiv CS.AI
•
ArXi:2603.12840v1 Announce Type: cross Voice anonymization masks vocal traits while preserving linguistic content, which may still leak speaker-specific patterns. To assess and strengthen privacy evaluation, we propose a dual-stream attacker that fuses spectral and self-supervised learning features via parallel encoders with a three-stage