top of page

Fangchen FENG 冯方辰

I am currently an assistant professor (maître de conférences) at Institut Galilée, Université Sorbonne Paris Nord (Paris 13). My research work is about image source separation. My teaching is about numerical signal and image processing. 

 

I previously worked at Laboratoire APC (Astroparticule & Cosmologie) as a post-doc researcher. My work at APC concentrates on the localization of Gravitational Wave (GW). 

fangchen.feng@univ-paris13.fr

Gretsi

Lille, France

26/08/2019~29/08/2019

RECENT EVENTS

Workshop:SPARS

Toulouse, France

01/07/2019~04/07/2019

DEMONSTRATION OF MY RESEARCH

One experiment for source separation of convolutive mixtures. I used the Multichannel Nonnegative Matrix Factorization algorithm (MNMF) and obtained pretty good separation.

 Sawada, H., Kameoka, H., Araki, S., & Ueda, N. (2013). Multichannel extensions of non-negative matrix factorization with complex-valued data. IEEE Transactions on Audio, Speech, and Language Processing, 21(5), 971-982.

One little experiment for music declipping. Contact me for the Matlab code inspired from Siedenburg, K., Kowalski, M., & Dörfler, M. (2014, May). Audio declipping with social sparsity. In 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1577-1581). IEEE.

bottom of page