File Download
There are no files associated with this item.
Supplementary

Citations:
 Scopus: 0
 Appears in Collections:
Article: A matrixpencil approach to blind separation of colored signals
Title  A matrixpencil approach to blind separation of colored signals 

Authors  
Issue Date  1998 
Citation  Ieee Transactions On Signal Processing, 1998, v. 46 n. 10, p. 2848 How to Cite? 
Abstract  The problem of blind source separation in additive noise is an important problem in speech, array, and acoustic signal processing. In general, this problem requires the use of higher order statistics of the received signals. Nonetheless, for many signal sources such as speed with distinct, nonwhite power spectral densities, secondorder statistics of the received signal mixture can be exploited for signal separation. While previous approaches often assume that additive noise is absent or that the noise correlation matrix is known, we propose a simple yet effective signal extraction method for signal source separation under unknown temporally white noise. This new and unbiased signal extractor is derived from the matrix pencil formed between output autocorrelation matrices at different delays. Based on the matrix pencil, an ESPRITtype algorithm is derived to get an optimal solution in the least square sense. Our method performs better than other secondorder statisticsbased algorithms when sensor noises are correlated. Simulation examples are presented. © 1998 IEEE. 
Persistent Identifier  http://hdl.handle.net/10722/155339 
ISSN  2015 Impact Factor: 2.624 2015 SCImago Journal Rankings: 2.004 
DC Field  Value  Language 

dc.contributor.author  Chang, C  en_HK 
dc.contributor.author  Ding, Z  en_HK 
dc.contributor.author  Yau, SF  en_HK 
dc.contributor.author  Chan, FHY  en_HK 
dc.date.accessioned  20120808T08:32:58Z   
dc.date.available  20120808T08:32:58Z   
dc.date.issued  1998  en_HK 
dc.identifier.citation  Ieee Transactions On Signal Processing, 1998, v. 46 n. 10, p. 2848  en_HK 
dc.identifier.issn  1053587X  en_HK 
dc.identifier.uri  http://hdl.handle.net/10722/155339   
dc.description.abstract  The problem of blind source separation in additive noise is an important problem in speech, array, and acoustic signal processing. In general, this problem requires the use of higher order statistics of the received signals. Nonetheless, for many signal sources such as speed with distinct, nonwhite power spectral densities, secondorder statistics of the received signal mixture can be exploited for signal separation. While previous approaches often assume that additive noise is absent or that the noise correlation matrix is known, we propose a simple yet effective signal extraction method for signal source separation under unknown temporally white noise. This new and unbiased signal extractor is derived from the matrix pencil formed between output autocorrelation matrices at different delays. Based on the matrix pencil, an ESPRITtype algorithm is derived to get an optimal solution in the least square sense. Our method performs better than other secondorder statisticsbased algorithms when sensor noises are correlated. Simulation examples are presented. © 1998 IEEE.  en_HK 
dc.language  eng  en_US 
dc.relation.ispartof  IEEE Transactions on Signal Processing  en_HK 
dc.title  A matrixpencil approach to blind separation of colored signals  en_HK 
dc.type  Article  en_HK 
dc.identifier.email  Chang, C: cqchang@eee.hku.hk  en_HK 
dc.identifier.authority  Chang, C=rp00095  en_HK 
dc.description.nature  link_to_subscribed_fulltext  en_US 
dc.identifier.scopus  eid_2s2.033747649195  en_HK 
dc.identifier.volume  46  en_HK 
dc.identifier.issue  10  en_HK 
dc.identifier.spage  2848  en_HK 
dc.identifier.epage  2848  en_HK 
dc.publisher.place  United States  en_HK 
dc.identifier.scopusauthorid  Chang, C=7407033052  en_HK 
dc.identifier.scopusauthorid  Ding, Z=7401550510  en_HK 
dc.identifier.scopusauthorid  Yau, SF=7202478362  en_HK 
dc.identifier.scopusauthorid  Chan, FHY=7202586429  en_HK 