I'm a Ph.D. student in the dept. of Electrical Engineering and Computer Science, Northwestern University.
I'm working with Bryan Pardo, in the Interactive Audio lab.
I'm interested in teaching machines to understand sounds in daily life (Computational Audition).
My 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.
I am fortunate to have collaborated with some amazing researchers and engineers from Adobe's Advanced Technology Labs, Gracenote's Media Technology Lab, and Orange Labs, France Telecom.
[read more]
Selected Publications
[complete list]
Note: Peer-reviewed conferences are the major publication forum in the Computational Audition field. ICASSP is the flagship conference of IEEE Signal Processing Society with overall acceptance rates of around 50% and less than 10% for oral presentation. ISMIR is the world's leading research forum on processing, searching, organizing and accessing music-related data, with less than 20% acceptance rate for oral presentations. LVA/ICA is a major event for researchers in the areas of source separation and data factorization.
J. Han, G. J. Mysore, and B. Pardo:
Audio Imputation using the Non-negative Hidden Markov Model.
Lecture
Notes in Computer Science: Latent Variable Analysis and Signal Separation (LVA/ICA), 2012. (Spotlight Presentation) [
pdf]
[
BibTex]
[
Webpage]
J.Han and C.Chen:
Improving melody extraction using Probabilistic Latent Component Analysis.
in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2011. (Oral Presentation: 7%) [
pdf] [
BibTex] [
Presentation]
J. Han and B. Pardo:
Reconstructing completely overlapped notes from musical mixtures.
in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2011. [
pdf] [
BibTex]
[
Poster]
Z. Duan,
J. Han, and B. Pardo:
Song-level multi-pitch tracking by heavily constrained clustering.
in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2010. (Oral Presentation: 8%) [
pdf] [
BibTex] [
Presentaion]
Z. Duan,
J. Han and B. Pardo:
Harmonically Informed Multi-pitch Tracking.
in Proc. International Society for Music Information Retrieval Conference (ISMIR), 2009. (Oral Presentation: 18%) [
pdf] [
BibTex]
[
Presentation]
M. Skalak,
J. Han, and B. Pardo:
Speeding Melody Search with Vantage Point Trees.
in Proc. International Society for Music Information Retrieval Conference (ISMIR), 2008. [
pdf] [
BibTex]
