DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cho, HY | ko |
dc.contributor.author | Kim, LY | ko |
dc.contributor.author | Oh, Yung-Hwan | ko |
dc.date.accessioned | 2010-03-22T08:45:28Z | - |
dc.date.available | 2010-03-22T08:45:28Z | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.issued | 2002-06 | - |
dc.identifier.citation | ELECTRONICS LETTERS, v.38, no.12, pp.611 - 612 | - |
dc.identifier.issn | 0013-5194 | - |
dc.identifier.uri | http://hdl.handle.net/10203/17269 | - |
dc.description.abstract | A new method for the recognition of speech that is partly corrupted by noise is proposed. For this purpose, the reliability of each speech segment is measured based on a log likelihood ratio. A segment that has higher reliability is given more importance in the decision making by a modified Viterbi algorithm. Experimental results showed that the method significantly improves the performance of isolated word recognition under various burst noise situations. | - |
dc.language | English | - |
dc.language.iso | en_US | en |
dc.publisher | INST ENGINEERING TECHNOLOGY-IET | - |
dc.title | Segmental reliability weighting for robust recognition of partly corrupted speech | - |
dc.type | Article | - |
dc.identifier.wosid | 000176632000052 | - |
dc.identifier.scopusid | 2-s2.0-0037030537 | - |
dc.type.rims | ART | - |
dc.citation.volume | 38 | - |
dc.citation.issue | 12 | - |
dc.citation.beginningpage | 611 | - |
dc.citation.endingpage | 612 | - |
dc.citation.publicationname | ELECTRONICS LETTERS | - |
dc.embargo.liftdate | 9999-12-31 | - |
dc.embargo.terms | 9999-12-31 | - |
dc.contributor.localauthor | Oh, Yung-Hwan | - |
dc.contributor.nonIdAuthor | Cho, HY | - |
dc.contributor.nonIdAuthor | Kim, LY | - |
dc.type.journalArticle | Article | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.