Highlighted Projects: FLAM (Frame-wise Language-Audio Modeling), CLAP (Contrastive Language-Audio Pretraining), HTS-AT (Hierarchical Audio Transformer), Music SketchNet (Controllable Algorithmic Music Composition), POP909 (A Dataset for Pop Music Arrangement), TONet (A Singing Melody Extraction Framework), Choral Music Separation.
Research Experience
Research Scientist at Adobe Research; Interned at Adobe, Mitsubishi Electric Research Laboratories (MERL), Apple, and other companies, focusing on music and general audio research.
Education
PhD in Computer Science, University of California San Diego (UCSD); Master in Music, University of California San Diego (UCSD); Bachelor's degree in Software Engineering, Fudan University.
Background
Main interest: Audio Processing and Analysis, and its application to downstreaming tasks. Inter-disciplinary among music, general audio, and technology, including Audio Representation Learning, Language-Audio Modeling, Audio Understanding, Audio Source Separation, Music Information Retrieval, etc.
Miscellany
Alias 'Knut' comes from one of his favorite composers, Knut Nystedt; Was the website maintainer of New Interfaces for Musical Expression.