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

All Science Journal Classification (ASJC) codes

  • Software

Fingerprint Dive into the research topics of 'Discriminative hidden Markov model recognizer with neural network postprocessor'. Together they form a unique fingerprint.

  • 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, .