4 papers
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…
Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models
Tae-Young Lee, Juwon Seo, Jong Hwan Ko +1
Recent advances in diffusion models have enabled high-quality synthesis of specific subjects, such as identities or objects. This capability, while unlocking new possibilities in c…
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…
TESU-LLM: Training Speech-LLMs Without Speech via Unified Encoder Alignment
Taesoo Kim, Jong Hwan Ko
Recent advances in speech-enabled language models have shown promising results in building intelligent voice assistants. However, most existing approaches rely on large-scale paire…