Single channel blind source separation using the best characteristic basis

Bin Gao; W. L. Woo; S. S. Dlay

doi:10.1109/ICTTA.2008.4530049

Single channel blind source separation using the best characteristic basis

Bin Gao^*, W. L. Woo, S. S. Dlay

^*Corresponding author for this work

Computer and Information Sciences Department

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Citations (Scopus)

Abstract

This paper proposes a novel technique for separating single channel recording of speech mixture using a hybrid of maximum likelihood and maximum a posteriori estimators. In addition, the new algorithm proposes a new approach that accounts for the time structure of the source signals by encoding them into a set of basis filters that are characteristically the most significant. Real time testing of the new algorithm has been conducted and the obtained results are very encouraging.

Original language	English
Title of host publication	2008 3rd International Conference on Information and Communication Technologis
Subtitle of host publication	From Theory to Applications, ICTTA
Publisher	IEEE
ISBN (Electronic)	9781424417520
ISBN (Print)	9781424417513
DOIs	https://doi.org/10.1109/ICTTA.2008.4530049
Publication status	Published - 23 May 2008
Event	2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications, ICTTA - Damascus, Syrian Arab Republic Duration: 7 Apr 2008 → 11 Apr 2008

Conference

Conference	2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications, ICTTA
Country/Territory	Syrian Arab Republic
City	Damascus
Period	7/04/08 → 11/04/08

Keywords

Blind source separation
Independent component analysis
ML and MAP estimation

Access to Document

10.1109/ICTTA.2008.4530049

Cite this

@inproceedings{57b4b6f4168c42c69bf521d10d0a1aff,

title = "Single channel blind source separation using the best characteristic basis",

abstract = "This paper proposes a novel technique for separating single channel recording of speech mixture using a hybrid of maximum likelihood and maximum a posteriori estimators. In addition, the new algorithm proposes a new approach that accounts for the time structure of the source signals by encoding them into a set of basis filters that are characteristically the most significant. Real time testing of the new algorithm has been conducted and the obtained results are very encouraging.",

keywords = "Blind source separation, Independent component analysis, ML and MAP estimation",

author = "Bin Gao and Woo, {W. L.} and Dlay, {S. S.}",

year = "2008",

month = may,

day = "23",

doi = "10.1109/ICTTA.2008.4530049",

language = "English",

isbn = "9781424417513",

booktitle = "2008 3rd International Conference on Information and Communication Technologis",

publisher = "IEEE",

address = "United States",

note = "2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications, ICTTA ; Conference date: 07-04-2008 Through 11-04-2008",

}

Gao, B, Woo, WL & Dlay, SS 2008, Single channel blind source separation using the best characteristic basis. in 2008 3rd International Conference on Information and Communication Technologis: From Theory to Applications, ICTTA. IEEE, 2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications, ICTTA, Damascus, Syrian Arab Republic, 7/04/08. https://doi.org/10.1109/ICTTA.2008.4530049

TY - GEN

T1 - Single channel blind source separation using the best characteristic basis

AU - Gao, Bin

AU - Woo, W. L.

AU - Dlay, S. S.

PY - 2008/5/23

Y1 - 2008/5/23

N2 - This paper proposes a novel technique for separating single channel recording of speech mixture using a hybrid of maximum likelihood and maximum a posteriori estimators. In addition, the new algorithm proposes a new approach that accounts for the time structure of the source signals by encoding them into a set of basis filters that are characteristically the most significant. Real time testing of the new algorithm has been conducted and the obtained results are very encouraging.

AB - This paper proposes a novel technique for separating single channel recording of speech mixture using a hybrid of maximum likelihood and maximum a posteriori estimators. In addition, the new algorithm proposes a new approach that accounts for the time structure of the source signals by encoding them into a set of basis filters that are characteristically the most significant. Real time testing of the new algorithm has been conducted and the obtained results are very encouraging.

KW - Blind source separation

KW - Independent component analysis

KW - ML and MAP estimation

U2 - 10.1109/ICTTA.2008.4530049

DO - 10.1109/ICTTA.2008.4530049

M3 - Conference contribution

AN - SCOPUS:49149099745

SN - 9781424417513

BT - 2008 3rd International Conference on Information and Communication Technologis

PB - IEEE

T2 - 2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications, ICTTA

Y2 - 7 April 2008 through 11 April 2008

ER -

Single channel blind source separation using the best characteristic basis

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this