DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, CH | ko |
dc.contributor.author | Lee, Soo-Young | ko |
dc.date.accessioned | 2009-07-23T02:42:05Z | - |
dc.date.available | 2009-07-23T02:42:05Z | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.issued | 2007-07 | - |
dc.identifier.citation | IEEE SIGNAL PROCESSING LETTERS, v.14, pp.489 - 491 | - |
dc.identifier.issn | 1070-9908 | - |
dc.identifier.uri | http://hdl.handle.net/10203/10215 | - |
dc.description.abstract | For noise-robust speech recognition, we incorporated a top-down attention mechanism into a hidden Markov model classifier with Mel-frequency cepstral coefficient features. The attention filter was introduced at the outputs of the Mel-scale filterbank and adjusted to maximize the log-likelihood of the attended features with the attended class. A low-complexity constraint was proposed to prevent the attention filter from over-fitting' and a confidence measure was introduced on the attention. A classification was made to the class with the maximum confidence measure, and demonstrated 54 % and 68 % reduction of the false recognition rate with 15-and 20-dB signal-to-noise ratio, respectively. | - |
dc.language | English | - |
dc.language.iso | en_US | en |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.subject | MODEL | - |
dc.title | Noise-robust speech recognition using top-down selective attention with an HMM classifier | - |
dc.type | Article | - |
dc.identifier.wosid | 000247407000015 | - |
dc.identifier.scopusid | 2-s2.0-34347375731 | - |
dc.type.rims | ART | - |
dc.citation.volume | 14 | - |
dc.citation.beginningpage | 489 | - |
dc.citation.endingpage | 491 | - |
dc.citation.publicationname | IEEE SIGNAL PROCESSING LETTERS | - |
dc.identifier.doi | 10.1109/LSP.2006.891326 | - |
dc.contributor.localauthor | Lee, Soo-Young | - |
dc.contributor.nonIdAuthor | Lee, CH | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | hidden Markov model (HMM) | - |
dc.subject.keywordAuthor | selective attention | - |
dc.subject.keywordAuthor | speech recognition | - |
dc.subject.keywordPlus | MODEL | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.