Jinyu Han is a Ph.D. student in the dept. of Electrical Engineering and Computer Science, Northwestern University. He's working with Bryan Pardo in the Interactive Audio lab. He's interested in teaching machines to understand sounds in daily life (Computational Audition). His primary research interests include machine learning, statiscal signal processing and their applications to Audio Processing, with a primary focus on music as a problem domain. I've done work on statistical modeling for audio, audio imputation and band extension, singing voice/melody extraction, audio source separation, multi-pitch tracking and query by humming.

Jinyu works with Gautham J. Mysore from Adobe's Advanced Technology Labs on Audio Imputation and Band extension, used to work in Gracenote's Media Technology Lab on Singing voice/Melody Extraction, and was an research intern at Orange Labs, France Telecom where he worked on Chinese Polyphone Disambiguation for Text-to-Speech system.
He serves as a reviewer for premium academic conferences (e.g., ICASSP, ISMIR, WASPAA and LVA/ICA) and several international journals such as IEEE Transaction on Audio, Speech, and Language Processing (IEEE TASLP), Journal of Signal, Image and Video Processing.

Jinyu Han received his B.E. in 2007 from Beijing University of Posts and Telecom (BUPT).

Jinyu likes Beatles, books, gangster movies, good clothes, and working out.

Jinyu fights dark forces in the moonlight.