███████╗██╗ ██╗███╗ ██╗ ██████╗ ██╗ ██╗██╗ ██╗██╗ ██╗███╗ ██╗ ██████╗██╗ ██╗ █████╗ ███╗ ██╗ ██████╗
██╔════╝██║ ██║████╗ ██║██╔════╝ ██║ ██╔╝╚██╗ ██╔╝██║ ██║████╗ ██║ ██╔════╝██║ ██║██╔══██╗████╗ ██║██╔════╝
███████╗██║ ██║██╔██╗ ██║██║ ███╗█████╔╝ ╚████╔╝ ██║ ██║██╔██╗ ██║ ██║ ███████║███████║██╔██╗ ██║██║ ███╗
╚════██║██║ ██║██║╚██╗██║██║ ██║██╔═██╗ ╚██╔╝ ██║ ██║██║╚██╗██║ ██║ ██╔══██║██╔══██║██║╚██╗██║██║ ██║
███████║╚██████╔╝██║ ╚████║╚██████╔╝██║ ██╗ ██║ ╚██████╔╝██║ ╚████║ ╚██████╗██║ ██║██║ ██║██║ ╚████║╚██████╔╝
╚══════╝ ╚═════╝ ╚═╝ ╚═══╝ ╚═════╝ ╚═╝ ╚═╝ ╚═╝ ╚═════╝ ╚═╝ ╚═══╝ ╚═════╝╚═╝ ╚═╝╚═╝ ╚═╝╚═╝ ╚═══╝ ╚═════╝
ML for music and audio
I am currently working as a research assistant on the “Automatic Music Performance Assessment & Feedback” project at the C4DM-QMUL funded by ABRSM. I also worked on the Multi-instrument Automatic Music Transcription (AMT) project at the C4DM, in collaboration with Huawei. Prior to that, I worked as a research scientist at Cochlear.ai for several years. I also worked as a researcher at Seoul National University's Institute for Industrial Systems Innovation, and Music and Audio Research Group (SNU-MARG).
Current Research Interests:
- Multimodal approach to music performance assessment and feedback
- A generative music model that interacts with humans through symbolic prompts
- Multi-task learning approach to low-resource music transcription
- Industry-scale music retrieval system and RAG