Presentation 2009-01-30
Blind Source Separation based on a simplified mixing model
Leandro Di Persia, Yoshihiro MORIMOTO, Masuzo YANAGIDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Permutation-Free ICA is a method that can avoid so-callled "Permutation problem" that appears in conventional frequency-domain ICA due to indeterminicity among sources in each frequency bin. Permutation-Free ICA carries out separation on a set of long vectors consisting of connected temporal changes of frequency components of the received signals. The separation matrix obtained in Permutation-Free ICA, however, has common directivity for all frequency bins. Presented in this report is a new method that generates a separation matrix for each frequency bin, based on a simplified mixing model having no permutations, retaining high processing speed.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Blind Source Separation / Independent Component Analysis / Permutation Problem / Simplified mixing model
Paper # EA2008-134
Date of Issue

Conference Information
Committee EA
Conference Date 2009/1/22(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Engineering Acoustics (EA)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Blind Source Separation based on a simplified mixing model
Sub Title (in English)
Keyword(1) Blind Source Separation
Keyword(2) Independent Component Analysis
Keyword(3) Permutation Problem
Keyword(4) Simplified mixing model
1st Author's Name Leandro Di Persia
1st Author's Affiliation Universidad National de Entre Rios()
2nd Author's Name Yoshihiro MORIMOTO
2nd Author's Affiliation Faculty of Engineering, Doshisha University
3rd Author's Name Masuzo YANAGIDA
3rd Author's Affiliation Faculty of Engineering, Doshisha University
Date 2009-01-30
Paper # EA2008-134
Volume (vol) vol.108
Number (no) 411
Page pp.pp.-
#Pages 6
Date of Issue