Independent Low-Rank Matrix Analysis Based on Generalized Kullback-Leibler Divergence

Shinichi MOGAMI  Yoshiki MITSUI  Norihiro TAKAMUNE  Daichi KITAMURA  Hiroshi SARUWATARI  Yu TAKAHASHI  Kazunobu KONDO  Hiroaki NAKAJIMA  Hirokazu KAMEOKA  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E102-A   No.2   pp.458-463
Publication Date: 2019/02/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.E102.A.458
Type of Manuscript: LETTER
Category: Engineering Acoustics
Keyword: 
blind source separation,  nonnegative matrix factorization,  Poisson distribution,  Kullback-Leibler divergence,  

Full Text: FreePDF(1.8MB)


Summary: 
In this letter, we propose a new blind source separation method, independent low-rank matrix analysis based on generalized Kullback-Leibler divergence. This method assumes a time-frequency-varying complex Poisson distribution as the source generative model, which yields convex optimization in the spectrogram estimation. The experimental evaluation confirms the proposed method's efficacy.