Mixed discriminant training of hybrid ANN/HMM systems for online handwritten word recognition

International Journal of Pattern Recognition and Artificial Intelligence

Volumn 21, Issue 1, 2007, Pages 117-134

  Caillault, Emilie ^a   Viard Gaudin, Christian ^a  

^a UNIVERSITÉ DE NANTES   (France)

Author keywords

Control of implicit segmentation; Hybrid ANN HMM system; Maximum mutual information maximum likelihood estimation (MMI MLE); Mixed discriminant criteria; Online cursive handwriting

Indexed keywords

DATA REDUCTION; MARKOV PROCESSES; MATHEMATICAL MODELS; ONLINE SYSTEMS; PATTERN RECOGNITION;

CONTROL OF IMPLICIT SEGMENTATION; HYBRID ANN/HMM SYSTEM; MAXIMUM MUTUAL INFORMATION/MAXIMUM LIKELIHOOD ESTIMATION (MMI/MLE); MIXED DISCRIMINANT CRITERIA; ONLINE CURSIVE HANDWRITING;

NEURAL NETWORKS;

EID: 33847355632     PISSN: 02180014     EISSN: None     Source Type: Journal    
DOI: 10.1142/S0218001407005338     Document Type: Conference Paper

References (16)

1. C. Bishop, Generative versus discriminative methods in computer vision, Invited Keynote Talk at ICPR, 2004, Cambridge, presented on 24, August 2004.
2. H. Bourlard and N. Morgan, Continuous speech recognition by connectionist statistical methods, IEEE Trans. Neural Networks 4(6) (1993) 893-909.
3. W. T. Chen and P. Gader, Word level discriminative training for handwritten word recognition, Proc. 7th IWFHR (2000), pp. 393-402.
4. M. A. Franzini, K.F. Lee and A. Waibel, Connectionist Viterbi training: a, new hybrid method for continuous speech recognition, Int. Conf. Acoustics, Speech and Signal Processing, Albuquerque (1990), pp. 417-420.
5. M. Gilloux, M. Leroux and J.-M. Bertille, Strategies for cursive script recognition using hidden Markov models, Mach. Vis. Appl. 8(4) (1995) 197-205.
6. S. Jaeger, S. Manke, J. Reichert and A. Waibel, Online handwriting recognition: the NPen++ recognizer, IJDAR'003 (2000) 169-180.
7. S. Knerr et al., Hidden Markov model based word recognition and its application to legal amount reading on French checks, Comput. Vis. Imag. Underst. 70(3) (1998) 404-419.
8. S. Knerr and E. Augustin, A neural network-hidden Markov model hybrid for cursive word recognition, ICPR. (1998).
9. R. Plamondon and S. N. Srihari, Online and offline handwriting recognition: a comprehensive survey, IEEE Trans. PAMI 22(1) (2000) 63-84.
10. L. R. Rabiner, A tutorial on hidden Markov models and selected applications in speech recognition, Proc. IEEE 77 (1989) 257-285.
11. G. Rigoll, Maximum mutual information neural networks for hybrid connectionistHMM speech recognition systems, IEEE Trans. Speech Audio. Process. 2(1) (1994) 175-1184.
12. M. Schenkel, I. Guyon and D. Henderson, Online cursive script recognition using time delay neural networks and hidden Markov models, Mach. Vis. Appl., Special Issue on Cursive Script Recognition 8 (1995) 215-223.
13. Y. H. Tay, P. M. Lallican, M. Khalid, S. Knerr and C. Viard-Gaudin, An analytical handwritten word recognition system with word-level discriminant training, Proc. Sixth ICDAR, Seattle (September 2001), pp. 726-730.
14. E. Trent in and M. Gori, A survey of hybrid ANN/HMM models for automatic speech recognition, Neurocomputing 37 (2001) 91-126.
15. C. Viard-Gaudin, P.-M. Lallican, P. Binter and S. Knerr, The Ireste ON/OFF (IRONOFF) dual handwriting database, Fifth Int. Conf. Document Analysis and Recognition (ICDAR) (1999), pp. 455-458.
16. C. Viard-Gaudin, P.-M. Lallican and S. Knerr, Recognition-directed recovering of temporal information form handwriting images, Patt. Recogn. Lett. 26 (2005) 2537-2548.