Tandem HMM with convolutional neural network for handwritten word recognition

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2013, Pages 2390-2394

  Bluche, Theodore ^a,b   Ney, Hermann ^b,c   Kermorvant, Christopher ^a  

^a A2iA SA   (France)

^b UFR 919 Laboratoire d'Informatique Pour la Mécanique et les Sciences de l'Ingénieur   (France)

^c RWTH AACHEN UNIVERSITY   (Germany)

Author keywords

Convolutional Neural Network; Handwriting recognition; Hidden Markov Model

Indexed keywords

CONVOLUTIONAL NEURAL NETWORK; EMISSION PROBABILITIES; FEATURE EXTRACTOR; GAUSSIAN MIXTURES; HAND WRITTEN CHARACTER RECOGNITION; HANDWRITING RECOGNITION; HANDWRITTEN WORD RECOGNITION; PIXEL VALUES;

CHARACTER RECOGNITION; PIXELS; RECURRENT NEURAL NETWORKS; SIGNAL PROCESSING; VOCABULARY CONTROL;

HIDDEN MARKOV MODELS;

EID: 84890474216     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2013.6638083     Document Type: Conference Paper

References (21)

1. A.-L. Bianne, F. Menasri, R. Al-Hajj, C. Mokbel,C. Kermorvant, and L. Likforman-Sulem, "Dynamicand Contextual Information in HMM modeling forHandwriting Recognition," IEEE Transactions on PatternAnalysis and Machine Intelligence, vol. 33, no. 10,pp. 2066-2080, 2011
2. N.Y. Hammerla, T. Plötz, S. Vajda, and G.A. Fink, "TowardsFeature Learning for HMM-based Offline HandwritingRecognition, " in International Workshop onFrontiers in Arabic Handwriting Recognition, 2010
3. F. Grezl, M. Karafiat, S. Kontar, and J. Cernocky, "Probabilisticand Bottle-Neck Features for LVCSR of Meetings,"in International Conference on Acoustics, Speechand Signal Processing, 2007, vol. 4, p. 757
4. G. Dahl and D. Yu, "Context-Dependent Pre-trainedDeep Neural Networks for Large Vocabulary SpeechRecognition," IEEE Transactions on Audio, Speech, andLanguage Processing, vol. 20, no. 1, pp. 30-42, 2012
5. P. Dreuw, P. Doetsch, C. Plahl, and H. Ney, "HierarchicalHybrid MLP/HMM or rather MLP Features for aDiscriminatively Trained Gaussian HMM: A Comparisonfor Offline Handwriting Recognition," in InternationalConference on Image Processing, 2011
6. P. Doetsch, "Optimization of hidden markov models andneural networks," M.S. thesis, RWTH Aachen University,Aachen, Germany, Dec. 2011
7. Y. Le Cun, K. Kavukcuoglu, and C. Farabet, "Convolutionalnetworks and applications in vision," InternationalSymposium on Circuits and Systems, pp. 253-256, May 2010
8. Y. Le Cun, L. Bottou, Y. Bengio, and P. Haffner,"Gradient-Based Learning Applied to DocumentRecognition," Proceedings of the IEEE, vol. 86, no. 11,pp. 2278-2324, 1998
9. D. C. Ciresan, U. Meier, L. M. Gambardella, andJ. Schmidhuber, "Convolutional Neural Network CommitteesFor Handwritten Character Classification," inInternational Conference of Document Analysis andRecognition, Beijing, 2011, vol. 10, pp. 1135-1139
10. Y. Bengio, Y. Le Cun, and D. Henderson, "Globallytrained handwritten word recognizer using spatial representation,convolutional neural networks and HiddenMarkov Models," in Neural Information ProcessingSystem, 1994
11. Y. Le Cun, L. Bottou, and Y. Bengio, "Reading checkswith multilayer graph transformer networks," in InternationalConference on Acoustics, Speech, and SignalProcessing, 1997
12. H. Bourlard and N. Morgan, Connectionist speechrecognition: a hybrid approach, Chapter 7, vol. 247of The Kluwer international series in engineering andcomputer science: VLSI, computer architecture, anddigital signal processing, Kluwer Academic Publishers,1994
13. H. Hermansky, D. P. W. Ellis, and S. Sharma, "Tandemconnectionist feature extraction for conventionalHMM systems," International Conference on AcousticsSpeech and Signal Processing, vol. 3, no. 28149,pp. 1635-1638, 2000
14. Y. Bengio, Y. Le Cun, C. Nohl, and C. Burges, "LeRec:a NN/HMM hybrid for on-line handwriting recognition.,"Neural Computation, vol. 7, no. 6, pp. 1289-1303, 1995
15. R. Buse, Z. Q. Liu, and T. Caelli, "A structural andrelational approach to handwritten word recognition.,"IEEE transactions on systems, man, and cybernetics,vol. 27, no. 5, pp. 847-61, Jan. 1997
16. A. Vinciarelli and J. Luettin, "A new normalisation techniquefor cursive handwritten words," Pattern RecognitionLetters, vol. 22, pp. 1043-1050, 2001
17. D. Povey, A. Ghoshal, G. Boulianne, L. Burget,O. Glembek, N. Goel, M. Hannemann, P. Motlicek,Y. Qian, P. Schwarz, J. Silovsky, G. Stemmer, andK. Vesely, "The kaldi speech recognition toolkit," inIEEE 2011 Workshop on Automatic Speech Recognitionand Understanding, Dec. 2011
18. E. Augustin, M. Carré, E. Grosicki, J.-M. Brodin, E. Geoffrois,and F. Preteux, "RIMES evaluation campaignfor handwritten mail processing," in Workshop on Frontiersin Handwriting Recognition, 2006, number 1
19. U. V. Marti and H. Bunke, "The IAM-database: an Englishsentence database for offline handwriting recognition,"International Journal on Document Analysis andRecognition, vol. 5, no. 1, pp. 39-46, 2002
20. F. Menasri, J. Louradour, A-L. Bianne-bernard, andC. Kermorvant, "The A2iA French handwriting recognitionsystem at the Rimes-ICDAR2011 competition,"in Document Recognition and Retrieval Conference,2012, vol. 8297
21. E. Grosicki and H. ElAbed, "ICDAR 2009 HandwritingRecognition Competition," in International Conferenceon Document Analysis and Recognition, 2009.