Showing cs.SDShow all
2 papers · 1 filter
cs.SD2026
Continual Speaker Identity Unlearning with Minimal Interference
Jinju Kim, Yunsung Kang, Gyeong-Moon Park +1
Machine unlearning removes designated concepts or knowledge from pre-trained models. Recent work has extended this paradigm to speaker identity unlearning in zero-shot text-to-spee…
cs.SD2025
Do Not Mimic My Voice: Speaker Identity Unlearning for Zero-Shot Text-to-Speech
Taesoo Kim, Jinju Kim, Dongchan Kim +2
The rapid advancement of Zero-Shot Text-to-Speech (ZS-TTS) technology has enabled high-fidelity voice synthesis from minimal audio cues, raising significant privacy and ethical con…