Existing voice-protection perturbations succeed only against naive attackers; a phoneme-guided purification-refinement pipeline restores cloneability of protected speech for most VC models.
Towards Understanding and Mitigating Audio Adversarial Examples for Speaker Recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning Attacks
Existing voice-protection perturbations succeed only against naive attackers; a phoneme-guided purification-refinement pipeline restores cloneability of protected speech for most VC models.