Showing cs.SDShow all
2 papers · 1 filter
cs.SD2026
Targeted Speaker Poisoning Framework in Zero-Shot Text-to-Speech
Thanapat Trachu, Thanathai Lertpetchpun, Sai Praneeth Karimireddy +1
Zero-shot Text-to-Speech (TTS) voice cloning poses severe privacy risks, demanding the removal of specific speaker identities from trained TTS models. Conventional machine unlearni…
cs.SD2025
Amplifying Artifacts with Speech Enhancement in Voice Anti-spoofing
Thanapat Trachu, Thanathai Lertpetchpun, Ekapol Chuangsuwanich
Spoofed utterances always contain artifacts introduced by generative models. While several countermeasures have been proposed to detect spoofed utterances, most primarily focus on…