Binaural semi-blind dereverberation of noisy convoluted speech signals

Cited 4 time in webofscience Cited 6 time in scopus
  • Hit : 426
  • Download : 1
DC FieldValueLanguage
dc.contributor.authorLee, Jong-Hwanko
dc.contributor.authorOh, Sang-Hoonko
dc.contributor.authorLee, Soo-Youngko
dc.date.accessioned2009-06-18T09:13:40Z-
dc.date.available2009-06-18T09:13:40Z-
dc.date.created2012-02-06-
dc.date.created2012-02-06-
dc.date.issued2008-12-
dc.identifier.citationNEUROCOMPUTING, v.72, pp.636 - 642-
dc.identifier.issn0925-2312-
dc.identifier.urihttp://hdl.handle.net/10203/9620-
dc.description.abstractIn order to overcome a limited performance of a conventional monaural model, this letter proposes a binaural blind dereverberation model. Its learning rule is derived using a blind least-squares measure by exploiting higher-order characteristics of output components. In order to prevent an unwanted whitening of speech signal, we adopt a semi-blind approach by employing a pre-determined whitening filter. The proposed model is evaluated using several simulated conditions and the results show better speech quality than those of the monaural model. The applicability of the model to the real environment is also shown by applying to real-recorded data. Especially, the proposed model attains much improved word error rates from 13.9 +/- 5.7(%) to 4.1 +/- 3.5(%) across 13 speakers for testing in the real speech recognition experiments. (c) 2008 Elsevier B.V. All rights reserved.-
dc.description.sponsorshipThe authors would like to thank the anonymous reviewers for their criticisms which improve this letter very much. Also, the authors thank Drs. Doh-Suk Kim and Hyung-Min Park for their fruitful discussions. This work was supported by the Brain Neuroinformatics Research Program sponsored by Korean Ministry of Commerce, Industry, and Energy.en
dc.languageEnglish-
dc.language.isoen_USen
dc.publisherELSEVIER SCIENCE BV-
dc.subjectSOURCE SEPARATION-
dc.subjectDECONVOLUTION-
dc.subjectDECOMPOSITION-
dc.subjectSYSTEMS-
dc.titleBinaural semi-blind dereverberation of noisy convoluted speech signals-
dc.typeArticle-
dc.identifier.wosid000261643700069-
dc.identifier.scopusid2-s2.0-55949137578-
dc.type.rimsART-
dc.citation.volume72-
dc.citation.beginningpage636-
dc.citation.endingpage642-
dc.citation.publicationnameNEUROCOMPUTING-
dc.identifier.doi10.1016/j.neucom.2008.07.005-
dc.embargo.liftdate9999-12-31-
dc.embargo.terms9999-12-31-
dc.contributor.localauthorLee, Soo-Young-
dc.contributor.nonIdAuthorOh, Sang-Hoon-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorIndependent component analysis-
dc.subject.keywordAuthorBlind dereverberation-
dc.subject.keywordAuthorBlind deconvolution-
dc.subject.keywordAuthorBlind least squares-
dc.subject.keywordAuthorSpeech enhancement-
dc.subject.keywordAuthorAutomatic speech recognition-
dc.subject.keywordPlusSOURCE SEPARATION-
dc.subject.keywordPlusDECONVOLUTION-
dc.subject.keywordPlusDECOMPOSITION-
dc.subject.keywordPlusSYSTEMS-
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 4 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0