表紙画像

New learning algorithm based on Hidden Markov Model (HMM) as stochastic modelling for pattern calssification

This study investigates the use discriminative training methods of minimum classification error (MCE) to estimate the parameter of hidden Markov model (HMM). The conventional training of HMM is based on the maximum likelihood estimation (MLE) which aims to model the true probabilistic distribution o...

詳細記述

保存先:
書誌詳細
主要な著者: Balakrishnan, Malarvili, Ting, Chee Ming, Shaikh Salleh, Sheikh Hussain
フォーマット: Monograph
言語:English
出版事項: Faculty of Biomedical Engineering and Health Science 2009
主題:
TA Engineering (General). Civil engineering (General)
オンライン･アクセス:http://eprints.utm.my/id/eprint/9734/1/78208.pdf
http://eprints.utm.my/id/eprint/9734/
タグ: タグ追加
タグなし, このレコードへの初めてのタグを付けませんか!
id my.utm.9734
record_format eprints
spelling my.utm.97342017-08-15T03:29:39Z http://eprints.utm.my/id/eprint/9734/ New learning algorithm based on Hidden Markov Model (HMM) as stochastic modelling for pattern calssification Balakrishnan, Malarvili Ting, Chee Ming Shaikh Salleh, Sheikh Hussain TA Engineering (General). Civil engineering (General) This study investigates the use discriminative training methods of minimum classification error (MCE) to estimate the parameter of hidden Markov model (HMM). The conventional training of HMM is based on the maximum likelihood estimation (MLE) which aims to model the true probabilistic distribution of the data in term of maximizing the likelihood. This requires sufficient training data and correct choice of probabilistic models, which in reality hardly achievable. The insufficient training data and incorrect modeling assumption of HMM often yield an incorrect and unreliable model. Instead of learning the true distribution, the MCE based training targeted to minimizing the probability of error is used to obtain optimal Bayes classification. The central idea of MCE based training is to define a continuous, differentiable loss function to approximate the actual performance error rate. Gradient based optimization methods can be used to minimize this loss. In this study the first order online generalized probabilistic descent is used as optimization methods. The continuous density HMM is used as the classifier structure in the MCE framework. The MCE based training is evaluated on speaker-independent Malay isolated digit recognition. The MCE training achieves the classification accuracy of 96.4% compared to 96.1% of using MLE with small improvement rate of 0.31%. The small vocabulary is unable to reflect the performance comparison of the two methods, the MLE training given sufficient training data is sufficient to provide optimal classification accuracy. Future work will extend the evaluation on difficult classification task such as phoneme classification, to better access the discriminative ability of the both methods. Faculty of Biomedical Engineering and Health Science 2009-08-31 Monograph NonPeerReviewed application/pdf en http://eprints.utm.my/id/eprint/9734/1/78208.pdf Balakrishnan, Malarvili and Ting, Chee Ming and Shaikh Salleh, Sheikh Hussain (2009) New learning algorithm based on Hidden Markov Model (HMM) as stochastic modelling for pattern calssification. Project Report. Faculty of Biomedical Engineering and Health Science, Skudai, Johor. (Unpublished)
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
language English
topic TA Engineering (General). Civil engineering (General)
spellingShingle TA Engineering (General). Civil engineering (General)
Balakrishnan, Malarvili
Ting, Chee Ming
Shaikh Salleh, Sheikh Hussain
New learning algorithm based on Hidden Markov Model (HMM) as stochastic modelling for pattern calssification
description This study investigates the use discriminative training methods of minimum classification error (MCE) to estimate the parameter of hidden Markov model (HMM). The conventional training of HMM is based on the maximum likelihood estimation (MLE) which aims to model the true probabilistic distribution of the data in term of maximizing the likelihood. This requires sufficient training data and correct choice of probabilistic models, which in reality hardly achievable. The insufficient training data and incorrect modeling assumption of HMM often yield an incorrect and unreliable model. Instead of learning the true distribution, the MCE based training targeted to minimizing the probability of error is used to obtain optimal Bayes classification. The central idea of MCE based training is to define a continuous, differentiable loss function to approximate the actual performance error rate. Gradient based optimization methods can be used to minimize this loss. In this study the first order online generalized probabilistic descent is used as optimization methods. The continuous density HMM is used as the classifier structure in the MCE framework. The MCE based training is evaluated on speaker-independent Malay isolated digit recognition. The MCE training achieves the classification accuracy of 96.4% compared to 96.1% of using MLE with small improvement rate of 0.31%. The small vocabulary is unable to reflect the performance comparison of the two methods, the MLE training given sufficient training data is sufficient to provide optimal classification accuracy. Future work will extend the evaluation on difficult classification task such as phoneme classification, to better access the discriminative ability of the both methods.
format Monograph
author Balakrishnan, Malarvili
Ting, Chee Ming
Shaikh Salleh, Sheikh Hussain
author_facet Balakrishnan, Malarvili
Ting, Chee Ming
Shaikh Salleh, Sheikh Hussain
author_sort Balakrishnan, Malarvili
title New learning algorithm based on Hidden Markov Model (HMM) as stochastic modelling for pattern calssification
title_short New learning algorithm based on Hidden Markov Model (HMM) as stochastic modelling for pattern calssification
title_full New learning algorithm based on Hidden Markov Model (HMM) as stochastic modelling for pattern calssification
title_fullStr New learning algorithm based on Hidden Markov Model (HMM) as stochastic modelling for pattern calssification
title_full_unstemmed New learning algorithm based on Hidden Markov Model (HMM) as stochastic modelling for pattern calssification
title_sort new learning algorithm based on hidden markov model (hmm) as stochastic modelling for pattern calssification
publisher Faculty of Biomedical Engineering and Health Science
publishDate 2009
url http://eprints.utm.my/id/eprint/9734/1/78208.pdf
http://eprints.utm.my/id/eprint/9734/
_version_ 1643645239372546048
score 13.251813

類似資料