File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: A multi-filter system for speech enhancement under low signal-to-noise ratios

TitleA multi-filter system for speech enhancement under low signal-to-noise ratios
Authors
KeywordsNoise Reduction
Optimization
Speech Echancement
Speech Recognition
Issue Date2009
PublisherAmerican Institute of Mathematical Sciences. The Journal's web site is located at http://aimsciences.org/journals/jimo/description.htm
Citation
Journal Of Industrial And Management Optimization, 2009, v. 5 n. 3, p. 671-682 How to Cite?
AbstractIn this paper, the problem of deteriorating performance of speech recognition under very low signal-to-noise ratios (SNR) is considered. In particular, for a given pre-trained speech recognizer and for a finite set of speech commands, we show that popular noise reduction methods have a mixed performance in speech recognition accuracy under very low SNR. Although most noise reduction methods are attempting to reduce speech distortion or to increase noise suppression, it does not necessarily improve speech recognition accuracy very much due to the complexity of the recognizer. We propose a new hybrid algorithm to optimize on the speech recognition accuracy directly by mixing different noise reduction methods together. We show that this method can indeed improve the accuracy significantly.
Persistent Identifierhttp://hdl.handle.net/10722/155919
ISSN
2015 Impact Factor: 0.776
2015 SCImago Journal Rankings: 0.639
ISI Accession Number ID
Funding AgencyGrant Number
Research Grants Council of HKSARPolyU 7191/06E
Hong Kong Polytechnic University
Funding Information:

The first author is supported by the Research Grants Council of HKSAR (PolyU 7191/06E) and the Research Committee of the Hong Kong Polytechnic University.

References

 

DC FieldValueLanguage
dc.contributor.authorYiu, KFCen_US
dc.contributor.authorChan, KYen_US
dc.contributor.authorLow, SYen_US
dc.contributor.authorNordholm, Sen_US
dc.date.accessioned2012-08-08T08:38:24Z-
dc.date.available2012-08-08T08:38:24Z-
dc.date.issued2009en_US
dc.identifier.citationJournal Of Industrial And Management Optimization, 2009, v. 5 n. 3, p. 671-682en_US
dc.identifier.issn1547-5816en_US
dc.identifier.urihttp://hdl.handle.net/10722/155919-
dc.description.abstractIn this paper, the problem of deteriorating performance of speech recognition under very low signal-to-noise ratios (SNR) is considered. In particular, for a given pre-trained speech recognizer and for a finite set of speech commands, we show that popular noise reduction methods have a mixed performance in speech recognition accuracy under very low SNR. Although most noise reduction methods are attempting to reduce speech distortion or to increase noise suppression, it does not necessarily improve speech recognition accuracy very much due to the complexity of the recognizer. We propose a new hybrid algorithm to optimize on the speech recognition accuracy directly by mixing different noise reduction methods together. We show that this method can indeed improve the accuracy significantly.en_US
dc.languageengen_US
dc.publisherAmerican Institute of Mathematical Sciences. The Journal's web site is located at http://aimsciences.org/journals/jimo/description.htmen_US
dc.relation.ispartofJournal of Industrial and Management Optimizationen_US
dc.subjectNoise Reductionen_US
dc.subjectOptimizationen_US
dc.subjectSpeech Echancementen_US
dc.subjectSpeech Recognitionen_US
dc.titleA multi-filter system for speech enhancement under low signal-to-noise ratiosen_US
dc.typeArticleen_US
dc.identifier.emailYiu, KFC:cedric@hkucc.hku.hken_US
dc.identifier.authorityYiu, KFC=rp00206en_US
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.doi10.3934/jimo.2009.5.671en_US
dc.identifier.scopuseid_2-s2.0-68049111237en_US
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-68049111237&selection=ref&src=s&origin=recordpageen_US
dc.identifier.volume5en_US
dc.identifier.issue3en_US
dc.identifier.spage671en_US
dc.identifier.epage682en_US
dc.identifier.isiWOS:000269239600018-
dc.publisher.placeUnited Statesen_US
dc.identifier.scopusauthoridYiu, KFC=24802813000en_US
dc.identifier.scopusauthoridChan, KY=25639498200en_US
dc.identifier.scopusauthoridLow, SY=7102636488en_US
dc.identifier.scopusauthoridNordholm, S=7005690573en_US

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats