DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Sung-Woong | ko |
dc.contributor.author | Yun, Sung-Rack | ko |
dc.contributor.author | Yoo, Chang-Dong | ko |
dc.date.accessioned | 2013-03-11T20:30:45Z | - |
dc.date.available | 2013-03-11T20:30:45Z | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.issued | 2011-09 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, v.19, no.7, pp.1999 - 2012 | - |
dc.identifier.issn | 1558-7916 | - |
dc.identifier.uri | http://hdl.handle.net/10203/100196 | - |
dc.description.abstract | This paper considers a large margin discriminative semi-Markov model (LMSMM) for phonetic recognition. The hidden Markov model (HMM) framework that is often used for phonetic recognition assumes only local statistical dependencies between adjacent observations, and it is used to predict a label for each observation without explicit phone segmentation. On the other hand, the semi-Markov model (SMM) framework allows simultaneous segmentation and labeling of sequential data based on a segment-based Markovian structure that assumes statistical dependencies among all the observations within a phone segment. For phonetic recognition which is inherently a joint segmentation and labeling problem, the SMM framework has the potential to perform better than the HMM framework at the expense of slight increase in computational complexity. The SMM framework considered in this paper is based on a non-probabilistic discriminant function that is linear in the joint feature map which attempts to capture long-range statistical dependencies among observations. The parameters of the discriminant function are estimated by a large margin learning framework for structured prediction. The parameter estimation problem in hand leads to an optimization problem with many margin constraints, and this constrained optimization problem is solved using a stochastic gradient descent algorithm. The proposed LMSMM outperformed the large margin discriminative HMM in the TIMIT phonetic recognition task. | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.subject | SPEECH RECOGNITION | - |
dc.subject | SEGMENT MODEL | - |
dc.subject | CLASSIFICATION | - |
dc.subject | HMM | - |
dc.title | Large Margin Discriminative Semi-Markov Model for Phonetic Recognition | - |
dc.type | Article | - |
dc.identifier.wosid | 000293734500013 | - |
dc.identifier.scopusid | 2-s2.0-79960665439 | - |
dc.type.rims | ART | - |
dc.citation.volume | 19 | - |
dc.citation.issue | 7 | - |
dc.citation.beginningpage | 1999 | - |
dc.citation.endingpage | 2012 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING | - |
dc.embargo.liftdate | 9999-12-31 | - |
dc.embargo.terms | 9999-12-31 | - |
dc.contributor.localauthor | Yoo, Chang-Dong | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Automatic speech recognition (ASR) | - |
dc.subject.keywordAuthor | large margin discriminative models | - |
dc.subject.keywordAuthor | semi-Markov models | - |
dc.subject.keywordAuthor | structured support vector machines | - |
dc.subject.keywordPlus | SPEECH RECOGNITION | - |
dc.subject.keywordPlus | SEGMENT MODEL | - |
dc.subject.keywordPlus | CLASSIFICATION | - |
dc.subject.keywordPlus | HMM | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.