DC Field | Value | Language |
---|---|---|
dc.contributor.author | Im, Jung-Hui | ko |
dc.contributor.author | Lee, Soo-Young | ko |
dc.date.accessioned | 2013-03-12T10:02:58Z | - |
dc.date.available | 2013-03-12T10:02:58Z | - |
dc.date.created | 2012-07-03 | - |
dc.date.created | 2012-07-03 | - |
dc.date.created | 2012-07-03 | - |
dc.date.issued | 2012-02 | - |
dc.identifier.citation | IEEE SIGNAL PROCESSING LETTERS, v.19, no.2, pp.111 - 114 | - |
dc.identifier.issn | 1070-9908 | - |
dc.identifier.uri | http://hdl.handle.net/10203/101977 | - |
dc.description.abstract | We present a new unified training scheme using a feature extractor and HMM classifiers for better speech recognition performance. Both feature extractor and classifier are trained simultaneously to minimize classification error. Multiframe features are extracted using spectro-temporal dynamics and the feature extractor is implemented as a multilayer network, which is trained by a backpropagation (BP) algorithm with the help of an HMM inversion algorithm. The initial parameter values of the feature extractor are set for Mel-frequency cepstral coefficients (MFCC) as well as their delta and acceleration components. The experiments for phoneme classification demonstrate the practicality of unified training. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | Unified Training of Feature Extractor and HMM Classifier for Speech Recognition | - |
dc.type | Article | - |
dc.identifier.wosid | 000308248500002 | - |
dc.identifier.scopusid | 2-s2.0-84862920388 | - |
dc.type.rims | ART | - |
dc.citation.volume | 19 | - |
dc.citation.issue | 2 | - |
dc.citation.beginningpage | 111 | - |
dc.citation.endingpage | 114 | - |
dc.citation.publicationname | IEEE SIGNAL PROCESSING LETTERS | - |
dc.identifier.doi | 10.1109/LSP.2011.2179647 | - |
dc.contributor.localauthor | Lee, Soo-Young | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Feature extraction | - |
dc.subject.keywordAuthor | feature learning | - |
dc.subject.keywordAuthor | speech recognition | - |
dc.subject.keywordAuthor | unified feature extractor and classifier | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.