DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, KY | ko |
dc.contributor.author | Lee, Soo-Young | ko |
dc.date.accessioned | 2013-02-27T14:53:03Z | - |
dc.date.available | 2013-02-27T14:53:03Z | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.issued | 2000-08 | - |
dc.identifier.citation | NEURAL PROCESSING LETTERS, v.12, no.1, pp.41 - 48 | - |
dc.identifier.issn | 1370-4621 | - |
dc.identifier.uri | http://hdl.handle.net/10203/69186 | - |
dc.description.abstract | Based on a psychological selective attention theory a new algorithm is developed to provide reliable out-of-vocabulary (OOV) rejection for speech recognition systems in noisy environments. The developed attention model is based on Broadbent's 'early filtering' theory, and the attention adaptation process utilizes a gradient-descent error minimization algorithm with error backpropagation rule. The developed model is applied to isolated-word recognition tasks, and much higher in-vocabulary recognition rates are achieved with the same out-of-vocabulary rejection rates. | - |
dc.language | English | - |
dc.publisher | KLUWER ACADEMIC PUBL | - |
dc.subject | RECOGNITION | - |
dc.title | Out-of-vocabulary rejection based on selective attention model | - |
dc.type | Article | - |
dc.identifier.wosid | 000089616800004 | - |
dc.identifier.scopusid | 2-s2.0-0034247405 | - |
dc.type.rims | ART | - |
dc.citation.volume | 12 | - |
dc.citation.issue | 1 | - |
dc.citation.beginningpage | 41 | - |
dc.citation.endingpage | 48 | - |
dc.citation.publicationname | NEURAL PROCESSING LETTERS | - |
dc.contributor.localauthor | Lee, Soo-Young | - |
dc.contributor.nonIdAuthor | Park, KY | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | error backpropagation | - |
dc.subject.keywordAuthor | noisy speech | - |
dc.subject.keywordAuthor | out-of-vocabulary rejection | - |
dc.subject.keywordAuthor | robust speech recognition | - |
dc.subject.keywordAuthor | selective attention | - |
dc.subject.keywordPlus | RECOGNITION | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.