Visual speech recognition using support vector machines

M. Gordan1, C. Kotropoulos2, I. Pitas2
1Technical University of Cluj-Napoca, Cluj-Napoca, Romania
2Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece

Tóm tắt

In this paper we propose a visual speech recognition network based on support vector machines. Each word of the dictionary is described as a temporal sequence of visemes. Each viseme is described by a support vector machine, and the temporal character of speech is modeled by integrating the support vector machines as nodes into a Viterbi decoding lattice. Experiments conducted on a small visual speech recognition task show a word recognition rate on the level of the best rates previously reported, even without training the state transition probabilities in the Viterbi lattice and using very simple features. This proves the suitability of support vector machines for visual speech recognition.

Từ khóa

#Speech recognition #Support vector machines #Mouth #Hidden Markov models #Dictionaries #Viterbi algorithm #Lattices #Active shape model #Real time systems #Informatics

Tài liệu tham khảo

10.1109/ICCV.1995.466899 movellan, 1995, Visual speech recognition with stochastic networks, Advances in neural information processing systems, 7 young, 1999, The HTK Book benoit, 1992, A set of French visemes for visual speech synthesis, Talking Machines Theories Models and Designs, 485 platt, 2000, Probabilistic outputs for support vector machines. and comparisons to regularized likelihood methods, Advances in Large Margin Classifiers 10.1006/cviu.1996.0570 0, The Carnegie Mellon University Pronouncing Dictionary v 0 6 cristianini, 2000, An Introduction to Support Vector Machines vapnik, 1998, Statistical Learning Theory 10.1109/AFGR.2000.840618 joachims, 1999, Making large-scale SVM learning practical, Advances in Kernel Methods - Support Vector Learning ganapathiraju, 2000, Hybrid SVM/HMM architectures for speech recognition, Proc of Speech Transcription Workshop