Exploring full-duplex real-time music generation, focusing on how generative AI can listen and respond while making music with users.
-
Delivered a lecture on 'Neural Networks for Music' and mentored capstone projects for the KAIST CT × AI Content Microdegree program.
-
Received the Best Student Paper Award for 'DDSP-Based Neural Vehicle Sound Synthesis from Driving Signals' at the 6th AES International Conference on Automotive Audio.
-
'AdaTT: Text-Guided Instrument Timbre Transfer with Target-Adaptive Structural Control' was accepted to INTERSPEECH 2026.
-
Presented 'AdaTT: Text-Guided Instrument Timbre Transfer with Target-Adaptive Structural Control' in Short Oral and Poster sessions at KSMI (한국음악정보학회) 2026.
-
Presented on 'AI Generative Models for Controllable Music and Foley Sound Synthesis' at KOBA (한국음향학회) 2026.
-
Ph.D. in Music and Audio Computing (MAC) Lab, KAIST
-
SORI Research Intern
-
Sony CSL Research Intern
-
M.S. in Music and Audio Computing (MAC) Lab, KAIST
-
B.S. in Art & Technology, Sogang University
Double major in Big Data Science
Recent Publications
-
AdaTT: Text-Guided Instrument Timbre Transfer with Target-Adaptive Structural Control
27th Annual Conference of the International Speech Communication Association (INTERSPEECH), 2026.
-
DDSP-Based Neural Vehicle Sound Synthesis from Driving Signals
6th AES International Conference on Automotive Audio, 2026.
Best Student Paper Award
-
Video-Foley: Two-Stage Video-To-Sound Generation via Temporal Event Condition for Foley Sound
IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), 2025.
-
Pitch-ControlNet: Continuous Pitch Control for Monophonic Instrument Sound Generation
Late-Breaking/Demo (LBD), 25th International Society for Music Information Retrieval Conference (ISMIR), 2024.