Exploring MPE/MWE Training for Chinese Handwriting Recognition

The HMM-based segmentation-free strategy for Chinese handwriting recognition has the merit that the model parameters can be trained with text line samples without annotation of character boundaries. However, the recognition performance has been limited to the general maximum likelihood estimation framework. In this paper, we investigate the discriminative training framework based on MPE/MWE criteria in the context of Chinese handwriting recognition for the first time. It optimizes a objective function that is a smooth measure of recognition error. Then EBW procedure is used to solve such criteria. Some key issues for robust MPE/MWE training are explored. We reveal that MPE/MWE requires more training samples, however, Chinese handwriting recognition poses severe data sparsity problem. We explore the sample synthesizing to help the training process. Experiments are conducted on Chinese handwriting database and the effectiveness of MPE/MWE training is manifested. In particular, at least 28% error reduction of recognition rates is observed in MPE/MWE training with 50 copies of synthetic sample when big ram is used to approximate the language model.

[1]  Biing-Hwang Juang,et al.  Minimum classification error rate methods for speech recognition , 1997, IEEE Trans. Speech Audio Process..

[2]  Mark J. F. Gales,et al.  The Application of Hidden Markov Models in Speech Recognition , 2007, Found. Trends Signal Process..

[3]  Alain Biem,et al.  Maximization of mutual information for offline Thai handwriting recognition , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Jonathan Le Roux,et al.  Discriminative Training for Large-Vocabulary Speech Recognition Using Minimum Classification Error , 2007, IEEE Transactions on Audio, Speech, and Language Processing.

[5]  Tamás Varga.  Off-line cursive handwriting recognition using synthetic training data , 2006 .

[6]  Tonghua Su,et al.  Chinese Handwriting Recognition: An Algorithmic Perspective , 2013, Springer Briefs in Electrical and Computer Engineering.

[7]  Salvatore D. Morgera,et al.  An improved MMIE training algorithm for speaker-independent, small vocabulary, continuous speech recognition , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[8]  Tanja Schultz,et al.  Generalized discriminative training for speech recognition , 2012 .

[9]  A. Nadas,et al.  A generalization of the Baum algorithm to rational objective functions , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[10]  Hui Jiang,et al.  Discriminative training of HMMs for automatic speech recognition: A survey , 2010, Comput. Speech Lang..

[11]  Lawrence K. Saul,et al.  Large Margin Hidden Markov Models for Automatic Speech Recognition , 2006, NIPS.

[12]  Cheng-Lin Liu,et al.  Segmentation-free recognizer based on enhanced four plane feature for realistic Chinese handwriting , 2008, 2008 19th International Conference on Pattern Recognition.

[13]  Thierry Artières,et al.  Regularized bundle methods for convex and non-convex risks , 2012, J. Mach. Learn. Res..

[14]  Cheng-Lin Liu,et al.  Improving HMM-Based Chinese Handwriting Recognition Using Delta Features and Synthesized String Samples , 2010, 2010 12th International Conference on Frontiers in Handwriting Recognition.

[15]  Philippe Dreuw,et al.  Probabilistic sequence models for image sequence processing and recognition , 2012 .

[16]  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.

[17]  Slava M. Katz,et al.  Estimation of probabilities from sparse data for the language model component of a speech recognizer , 1987, IEEE Trans. Acoust. Speech Signal Process..

[18]  Steve J. Young,et al.  MMIE training of large vocabulary recognition systems , 1997, Speech Communication.

[19]  Cheng-Lin Liu,et al.  Lexicon-Driven Segmentation and Recognition of Handwritten Character Strings for Japanese Address Reading , 2002, IEEE Trans. Pattern Anal. Mach. Intell..