Members

morateng (at) skku.edu

Efficient speech dialogue systems, Style-controllable TTS, Parameter-efficient fine-tuning (PEFT)

yj.lee (at) g.skku.edu

Style-controllable TTS, Persona for LLM, Efficient speech processing

shinjh0729 (at) g.skku.edu

Efficient and real-time TTS, Multimodal conversational AI, Music for chatbots

mppn98 (at) g.skku.edu

Flow matching-based speech synthesis, Efficient TTS model design, Personalized speech enhancement

hyoeunkim (at) g.skku.edu

Personalized speech models, Efficient model approximation, On-device deployment

sbkim2345 (at) g.skku.edu

Efficient speech synthesis, Generative modeling, Speculative decoding

yoonji4024 (at) g.skku.edu

Speech and language modeling, Retrieval-augmented multimodal learning, Long-form speech synthesis

firstri (at) g.skku.edu

Multimodal LLM, GenAI hallucination mitigation, Speech and language AI

emily.choi (at) g.skku.edu

Efficient speech enhancement, Neural audio codec design, Autoregressive speech modeling

qkrtpdnd0802 (at) g.skku.edu

Diffusion language models, Efficient speech recognition, Model optimization

yj090744 (at) g.skku.edu

Personalized music preference modeling, Context-aware music recommendation, Audio-text retrieval

hoseong8115 (at) g.skku.edu

Multimodal hallucination mitigation, Contextual biasing, Speech Recognition

jyunchae (at) g.skku.edu

Rare-word speech recognition, Contextual biasing, Spoken language understanding