An HMM/MLP Architecture for Sequence Recognition

This paper presents a hybrid architecture of hidden Markov models (HMMs) and a multilayer perceptron (MLP). This exploits the discriminative capability of a neural network classifier while using HMM formalism to capture the dynamics of input patterns. The main purpose is to improve the discriminative power of the HMM-based recognizer by additionally classifying the likelihood values inside them with an MLP classifier. To appreciate the performance of the presented method, we apply it to the recognition problem of on-line handwritten characters. Simulations show that the proposed architecture leads to a significant improvement in generalization performance over conventional approaches to sequential pattern recognition.

[1]  Michael I. Jordan.  Serial Order: A Parallel Distributed Processing Approach , 1997 .

[2]  Harvey F. Silverman,et al.  Combining hidden Markov model and neural network classifiers , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[3]  S. Young.  Competitive training in hidden Markov models , 1990 .

[4]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[5]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[6]  Lalit R. Bahl,et al.  Maximum mutual information estimation of hidden Markov model parameters for speech recognition , 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[7]  Yoshua Bengio,et al.  Global optimization of a neural network-hidden Markov model hybrid , 1992, IEEE Trans. Neural Networks.

[8]  Pierre Baldi,et al.  Hybrid Modeling, HMM/NN Architectures, and Protein Applications , 1996, Neural Computation.

[9]  Hervé Bourlard,et al.  Continuous speech recognition using multilayer perceptrons with hidden Markov models , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[10]  A. Kundu,et al.  Recognition of handwritten script: a hidden Markov model based approach , 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

[11]  Richard P. Lippmann,et al.  Review of Neural Networks for Speech Recognition , 1989, Neural Computation.

[12]  Herbert Freeman,et al.  Computer Processing of Line-Drawing Images , 1974, CSUR.

[13]  Kin Hong Wong,et al.  Script recognition using hidden Markov models , 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[14]  K. S. Swarup,et al.  PATTERN CLASSIFICATION USING NEURAL NETWORKS FOR DIAGNOSTIC PROBLEM SOLVING , 1992 .

[15]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[16]  R.P. Lippmann,et al.  Pattern classification using neural networks , 1989, IEEE Communications Magazine.

[17]  Paramvir Bahl,et al.  Recognition of handwritten word: First and second order hidden Markov model based approach , 1989, Pattern Recognit..

[18]  Yves Lecourtier,et al.  Recognition of handwritten words using stochastic models , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[19]  Paramvir Bahl,et al.  Recognition of handwritten word: first and second order hidden Markov model based approach , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.