Approximate maximum likelihood source separation using the natural gradient

被引：0

作者：

Choi, S ^{[1
]}

Cichocki, A

Zhang, LQ

Amari, S

机构：

[1] POSTECH, Dept Comp Sci & Engn, Pohang, South Korea

[2] RIKEN, BSI, Brain Style Informat Syst Res Grp, Wako, Saitama 3510198, Japan

来源：

IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES | 2003年 / E86A卷 / 01期

关键词：

independent component analysis; maximum likelihood estimation; natural gradient; source separation; overdetermined mixtures;

D O I：

暂无

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper addresses a maximum likelihood method for source separation in the case of overdetermined mixtures corrupted by additive white Gaussian noise. We consider an approximate likelihood which is based on the Laplace approximation and develop a natural gradient adaptation algorithm to find a local maximum of the corresponding approximate likelihood. We present a detailed mathematical derivation of the algorithm using the Lie group invariance. Useful behavior of the algorithm is verified by numerical experiments.

引用

页码：198 / 205

页数：8

共 50 条

[41] Binaural source separation based on spatial cues and maximum likelihood model adaptation
Abdipour, Roohollah
Akbari, Ahmad
Rahmani, Mohsen
Nasersharif, Babak
DIGITAL SIGNAL PROCESSING, 2015, 36 : 174 - 183
[42] Near field source separation improvement through unconditional maximum likelihood estimator
Bonilla-Hernandez, Dario
Covarrubias-Rosales, David H.
Arceo-Olague, Jose G.
IEEE Latin America Transactions, 2006, 4 (06) : 403 - 408
[43] ONLINE SPEECH SOURCE SEPARATION BASED ON MAXIMUM LIKELIHOOD OF LOCAL GAUSSIAN MODELING
Togami, Masahito
2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2011, : 213 - 216
[44] Maximum likelihood blind source separation: A context-sensitive generalization of ICA
Pearlmutter, BA
Parra, LC
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 9: PROCEEDINGS OF THE 1996 CONFERENCE, 1997, 9 : 613 - 619
[45] Natural gradient multichannel blind deconvolution and source separation using causal FIR filters
Douglas, SC
Sawada, H
Makino, S
2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL V, PROCEEDINGS: DESIGN AND IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS INDUSTRY TECHNOLOGY TRACKS MACHINE LEARNING FOR SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING SIGNAL PROCESSING FOR EDUCATION, 2004, : 477 - 480
[46] A Modified Natural Gradient Algorithm for Blind Source Separation Using Generalized Constant Modulus
Gu, Fanglin
Zhang, Hang
Zhang, Jiang
Zhu, Desheng
Luo, Pan
2013 36TH INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS AND SIGNAL PROCESSING (TSP), 2013, : 663 - 666
[47] Using piecewise linear nonlinearities in the natural gradient and fastICA algorithms for blind source separation
Chao, Jih-Cheng
Douglas, Scott C.
2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 1813 - +
[48] Approximate maximum likelihood estimation of the Bingham distribution
Bee, Marco
Benedetti, Roberto
Espa, Giuseppe
COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2017, 108 : 84 - 96
[49] APPROXIMATE MAXIMUM-LIKELIHOOD FREQUENCY ESTIMATION
STOICA, P
HANDEL, P
SODERSTROM, T
AUTOMATICA, 1994, 30 (01) : 131 - 145
[50] Exact and approximate maximum likelihood localization algorithms
Chan, YT
Hang, HYC
Ching, PC
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2006, 55 (01) : 10 - 16

← 1 2 3 4 5 →