A blind source separation of instantaneous acoustic mixtures using natural gradient method

A variety of applications concerning communication signal processing involves recovering unobserved signals or 'sources' from several observed mixtures, and 'cocktail party effect' is a good paradigm related to this process. Given a set of linearly superimposed acoustic signals w...

Full description

Saved in:
Bibliographic Details
Main Authors: Sandiko, Christopher M., Magsino, Elmer R.
Format: text
Published: Animo Repository 2012
Subjects:
Online Access:https://animorepository.dlsu.edu.ph/faculty_research/2343
https://animorepository.dlsu.edu.ph/context/faculty_research/article/3342/type/native/viewcontent
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: De La Salle University
id oai:animorepository.dlsu.edu.ph:faculty_research-3342
record_format eprints
spelling oai:animorepository.dlsu.edu.ph:faculty_research-33422021-08-24T08:20:47Z A blind source separation of instantaneous acoustic mixtures using natural gradient method Sandiko, Christopher M. Magsino, Elmer R. A variety of applications concerning communication signal processing involves recovering unobserved signals or 'sources' from several observed mixtures, and 'cocktail party effect' is a good paradigm related to this process. Given a set of linearly superimposed acoustic signals without knowledge about the sources makes Blind Source Separation (BSS) a very suitable scheme. A more popular approach of BSS, Independent Component Analysis, has been exploited which basically senses the statistical independence of the source signal estimates to achieve separation. A set of interfering signals present in a typical acoustic environment has been instantaneously combined with a pre-determined mixing matrix. A great weight has been given on an excellent rendition of the Infomax technique of Independent Component Analysis (ICA), called the Natural Gradient Method, to employ a cost function that would yield an optimized de-mixing matrix, producing fairly estimated source signals. By varying the learning rate and the score function, a robust performance of the Natural Gradient has been exhibited, maximizing the separation quality, stability and convergence speed. © 2012 IEEE. 2012-01-01T08:00:00Z text text/html https://animorepository.dlsu.edu.ph/faculty_research/2343 https://animorepository.dlsu.edu.ph/context/faculty_research/article/3342/type/native/viewcontent Faculty Research Work Animo Repository Blind source separation Independent component analysis Auditory selective attention Electrical and Computer Engineering
institution De La Salle University
building De La Salle University Library
continent Asia
country Philippines
Philippines
content_provider De La Salle University Library
collection DLSU Institutional Repository
topic Blind source separation
Independent component analysis
Auditory selective attention
Electrical and Computer Engineering
spellingShingle Blind source separation
Independent component analysis
Auditory selective attention
Electrical and Computer Engineering
Sandiko, Christopher M.
Magsino, Elmer R.
A blind source separation of instantaneous acoustic mixtures using natural gradient method
description A variety of applications concerning communication signal processing involves recovering unobserved signals or 'sources' from several observed mixtures, and 'cocktail party effect' is a good paradigm related to this process. Given a set of linearly superimposed acoustic signals without knowledge about the sources makes Blind Source Separation (BSS) a very suitable scheme. A more popular approach of BSS, Independent Component Analysis, has been exploited which basically senses the statistical independence of the source signal estimates to achieve separation. A set of interfering signals present in a typical acoustic environment has been instantaneously combined with a pre-determined mixing matrix. A great weight has been given on an excellent rendition of the Infomax technique of Independent Component Analysis (ICA), called the Natural Gradient Method, to employ a cost function that would yield an optimized de-mixing matrix, producing fairly estimated source signals. By varying the learning rate and the score function, a robust performance of the Natural Gradient has been exhibited, maximizing the separation quality, stability and convergence speed. © 2012 IEEE.
format text
author Sandiko, Christopher M.
Magsino, Elmer R.
author_facet Sandiko, Christopher M.
Magsino, Elmer R.
author_sort Sandiko, Christopher M.
title A blind source separation of instantaneous acoustic mixtures using natural gradient method
title_short A blind source separation of instantaneous acoustic mixtures using natural gradient method
title_full A blind source separation of instantaneous acoustic mixtures using natural gradient method
title_fullStr A blind source separation of instantaneous acoustic mixtures using natural gradient method
title_full_unstemmed A blind source separation of instantaneous acoustic mixtures using natural gradient method
title_sort blind source separation of instantaneous acoustic mixtures using natural gradient method
publisher Animo Repository
publishDate 2012
url https://animorepository.dlsu.edu.ph/faculty_research/2343
https://animorepository.dlsu.edu.ph/context/faculty_research/article/3342/type/native/viewcontent
_version_ 1709757498587611136