Discriminative hidden Markov model recognizer with neural network postprocessor

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

This paper is concerned with the problem of improving recognition accuracy of hidden Markov models (HMM) for sequential pattern recognition. It is argued that maximum-likelihood estimation of the HMM parameters via the forward-backward algorithm may not lead to values which maximize recognition accuracy. We introduce a hybrid method with neural network postprocessor which is aimed at minimizing the number of recognition errors. This method exploits the discrimination capability of neural network classifier while using HMM formalism to capture the dynamics of input patterns. Although it has not been proved that the presented method is a kind of maximum mutual information estimation, experimental results with on-line handwriting characters suggest that it leads to fewer recognition errors than can be obtained with the conventional recognition method.

Original languageEnglish
Pages2881-2884
Number of pages4
Publication statusPublished - 1994 Dec 1
EventProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA
Duration: 1994 Jun 271994 Jun 29

Other

OtherProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)
CityOrlando, FL, USA
Period94/6/2794/6/29

Fingerprint

Hidden Markov models
Neural networks
Maximum likelihood estimation
Pattern recognition
Classifiers

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Cho, S. B. (1994). Discriminative hidden Markov model recognizer with neural network postprocessor. 2881-2884. Paper presented at Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7), Orlando, FL, USA, .
Cho, Sung Bae. / Discriminative hidden Markov model recognizer with neural network postprocessor. Paper presented at Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7), Orlando, FL, USA, .4 p.
@conference{3afcc1c404954946969bb04479917ee5,
title = "Discriminative hidden Markov model recognizer with neural network postprocessor",
abstract = "This paper is concerned with the problem of improving recognition accuracy of hidden Markov models (HMM) for sequential pattern recognition. It is argued that maximum-likelihood estimation of the HMM parameters via the forward-backward algorithm may not lead to values which maximize recognition accuracy. We introduce a hybrid method with neural network postprocessor which is aimed at minimizing the number of recognition errors. This method exploits the discrimination capability of neural network classifier while using HMM formalism to capture the dynamics of input patterns. Although it has not been proved that the presented method is a kind of maximum mutual information estimation, experimental results with on-line handwriting characters suggest that it leads to fewer recognition errors than can be obtained with the conventional recognition method.",
author = "Cho, {Sung Bae}",
year = "1994",
month = "12",
day = "1",
language = "English",
pages = "2881--2884",
note = "Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) ; Conference date: 27-06-1994 Through 29-06-1994",

}

Cho, SB 1994, 'Discriminative hidden Markov model recognizer with neural network postprocessor', Paper presented at Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7), Orlando, FL, USA, 94/6/27 - 94/6/29 pp. 2881-2884.

Discriminative hidden Markov model recognizer with neural network postprocessor. / Cho, Sung Bae.

1994. 2881-2884 Paper presented at Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7), Orlando, FL, USA, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Discriminative hidden Markov model recognizer with neural network postprocessor

AU - Cho, Sung Bae

PY - 1994/12/1

Y1 - 1994/12/1

N2 - This paper is concerned with the problem of improving recognition accuracy of hidden Markov models (HMM) for sequential pattern recognition. It is argued that maximum-likelihood estimation of the HMM parameters via the forward-backward algorithm may not lead to values which maximize recognition accuracy. We introduce a hybrid method with neural network postprocessor which is aimed at minimizing the number of recognition errors. This method exploits the discrimination capability of neural network classifier while using HMM formalism to capture the dynamics of input patterns. Although it has not been proved that the presented method is a kind of maximum mutual information estimation, experimental results with on-line handwriting characters suggest that it leads to fewer recognition errors than can be obtained with the conventional recognition method.

AB - This paper is concerned with the problem of improving recognition accuracy of hidden Markov models (HMM) for sequential pattern recognition. It is argued that maximum-likelihood estimation of the HMM parameters via the forward-backward algorithm may not lead to values which maximize recognition accuracy. We introduce a hybrid method with neural network postprocessor which is aimed at minimizing the number of recognition errors. This method exploits the discrimination capability of neural network classifier while using HMM formalism to capture the dynamics of input patterns. Although it has not been proved that the presented method is a kind of maximum mutual information estimation, experimental results with on-line handwriting characters suggest that it leads to fewer recognition errors than can be obtained with the conventional recognition method.

UR - http://www.scopus.com/inward/record.url?scp=0028735195&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028735195&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0028735195

SP - 2881

EP - 2884

ER -

Cho SB. Discriminative hidden Markov model recognizer with neural network postprocessor. 1994. Paper presented at Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7), Orlando, FL, USA, .