论文信息 - Minimum classification error training of hidden Markov models for handwriting recognition

Minimum classification error training of hidden Markov models for handwriting recognition

This paper evaluates the application of minimum classification error (MCE) training to online-handwritten text recognition based on hidden Markov models. We describe an allograph-based, character level MCE training aimed at minimizing the character error rate while enabling flexibility in writing style. Experiments on a writer-independent discrete character recognition task, covering all alpha-numerical characters and keyboard symbols, show that MCE achieves more than 30% character error rate reduction compared to the baseline maximum likelihood-based system.

Alain Biem

[1] Biing-Hwang Juang,et al. The segmental K-means algorithm for estimating parameters of hidden Markov models , 1990, IEEE Trans. Acoust. Speech Signal Process..

[2] Scott E. Fahlman,et al. An empirical study of learning speed in back-propagation networks , 1988 .

[3] Hiroshi Maruyama,et al. Real-time on-line unconstrained handwriting recognition using statistical methods , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[4] Biing-Hwang Juang,et al. Discriminative learning for minimum error classification [pattern recognition] , 1992, IEEE Trans. Signal Process..

[5] A. Nadas,et al. A decision theorectic formulation of a training problem in speech recognition and a comparison of training by unconditional versus conditional maximum likelihood , 1983 .

[6] Alain Biem,et al. Pattern recognition using discriminative feature extraction , 1997, IEEE Trans. Signal Process..

[7] Biing-Hwang Juang,et al. New discriminative training algorithms based on the generalized probabilistic descent method , 1991, Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop.