Confidence-based discriminative training for model adaptation in offline Arabic handwriting recognition

Proceedings of the International Conference on Document Analysis and Recognition, ICDAR

Volumn , Issue , 2009, Pages 596-600

  Dreuw, Philippe ^a   Heigold, Georg ^a   Ney, Hermann ^a  

^a RWTH AACHEN UNIVERSITY   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

ADAPTIVE TRAINING; ARABIC HANDWRITING; ARABIC HANDWRITING RECOGNITION SYSTEMS; DECODING PROCESS; DISCRIMINATIVE TRAINING; MAXIMUM MUTUAL INFORMATION; MODEL ADAPTATION; OFFLINE; UNSUPERVISED CLUSTERING; WRITING STYLE;

DECODING; FEATURE EXTRACTION; HIDDEN MARKOV MODELS; MAXIMUM LIKELIHOOD ESTIMATION; STEREOPHONIC BROADCASTING;

CHARACTER RECOGNITION;

EID: 71249102605     PISSN: 15205363     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICDAR.2009.116     Document Type: Conference Paper

References (18)

1. T. Anastasakos and S. Balakrishnan. The use of confidence measures in unsupervised adaptation of speech recognizers. In International Conference on Spoken Language Processing, Sydney, Australia, 1998.
2. R. Bertolami and H. Bunke. Hmm-based ensamble methods for offline handwritten text line recognition. Pattern Recognition, 41:3452-3460, 2008.
3. P. Dreuw, S. Jonas, and H. Ney. White-space models for offline arabic handwriting recognition. In International Conference on Pattern Recognition, Tampa, Florida, USA, Dec. 2008.
4. P. Dreuw, D. Rybach, C. Gollan, and H. Ney. Writer adaptive training and writing variant model refinement for offline arabic handwriting recognition. In ICDAR, Barcelona, Spain, July 2009.
5. G. A. Fink and T. Plötz. Unsupervised estimation of writing style models for improved unconstrained off-line handwriting recognition. In International Workshop on Frontiers in Handwriting Recognition, La Baule, France, Oct. 2006.
6. C. Gollan and M. Bacchiani. Confidence scores for acoustic model adaptation. In IEEE International Conference on Acoustics, Speech, and Signal Processing, pages 4289-4292, Las Vegas, NV, USA, Apr. 2008.
7. G. Heigold, T. Deselaers, R. Schlüter, and H. Ney. Modified mmi/mpe: A direct evaluation of the margin in speech recognition. In International Conference on Machine Learning, pages 384-391, Helsinki, Finland, July 2008.
8. G. Heigold, R. Schlüter, and H. Ney. On the equivalence of Gaussian HMM and Gaussian HMM-like hidden conditional random fields. In Interspeech, Antwerp, Belgium, Aug. 2007.
9. T. Jebara. Discriminative, generative, and imitative learning. PhD thesis, Massachusetts Institute of Technology, 2002.
10. T. Kemp and T. Schaaf. Estimating confidence using word lattices. In European Conference on Speech Communication and Technology, Rhodes, Greece, 1997.
11. V. Märgner and H. E. Abed. ICDAR 2007 Arabic handwriting recognition competition. In ICDAR, volume 2, pages 1274-1278, Sept. 2007.
12. V. Märgner, M. Pechwitz, and H. Abed. ICDAR 2005 Arabic handwriting recognition competition. In ICDAR, volume 1, pages 70-74, Seoul, Korea, Aug. 2005.
13. R. Nopsuwanchai and D. Povey. Discriminative training for HMM-based offline handwritten character recognition. In ICDAR, pages 114-118, 2003.
14. M. Padmanabhan, G. Saon, and G. Zweig. Lattice-based unsupervised mllr for speaker adaptation. In ISCA ITRW Automatic Speech Recognition: Challenges for the Millenium, Paris, France, 2000.
15. M. Pechwitz, S. S. Maddouri, V. Mägner, N. Ellouze, and H. Amiri. IFN/ENIT-database of handwritten Arabic words. In Colloque International Francophone sur l'Ecrit et le Document (CIFED), Hammamet, Tunis, Oct. 2002.
16. M. Pitz, F.Wessel, and H. Ney. Improved mllr speaker adaptation using confidence measures for conversational speech recognition. In International Conference on Spoken Language Processing, Beijing, China, 2000.
17. D. Povey and P. C. Woodland. Minimum phone error and I-smoothing for improved discriminative training. In International Conference on Acoustics, Speech, and Signal Processing, volume 1, Orlando, FL, 2002.
18. J. Zhang, R. Jin, Y. Yang, and A. Hauptmann. Modified logistic regression: An approximation to SVM and its applications in large-scale text categorization. In International Conference on Machine Learning, Aug. 2003.