Neural networks for statistical inference: Generalizations with applications to speech recognition
作者： H. Bourlard , N. Morgan
DOI: 10.1109/IJCNN.1991.170411
关键词:
摘要: The basic principles of the hybrid HMM/MLP (hidden Markov model/multilayer perceptron) approach are reviewed and extended to triphone models. It is also shown how statistical interpretation MLP output values can act upon development other algorithms help them understand their behavior, which case with a priori probabilities radial basis function networks. advantages speech recognition system incorporating both MLPs HMMs best discrimination ability incorporate multiple sources evidence (features, temporal context) without restrictive assumptions distributions or independence. >
sci-hub.se 参考文章(10)
D.B. Paul, J.K. Baker, J.M. Baker, On the interaction between true source, training, and testing language models international conference on acoustics, speech, and signal processing. pp. 569- 572 ,(1991) , 10.1109/ICASSP.1991.150403
Hervé Bourlard, Nelson Morgan, A Continuous Speech Recognition System Embedding MLP into HMM neural information processing systems. ,vol. 2, pp. 186- 193 ,(1989)
Kay-Fu Lee, Context-independent phonetic hidden Markov models for speaker-independent continuous speech recognition IEEE Transactions on Acoustics, Speech, and Signal Processing. ,vol. 38, pp. 347- 366 ,(1990) , 10.1007/978-3-642-76626-8_15
X.D. Huang, M.A. Jack, Semi-continuous hidden Markov models for speech signals Computer Speech & Language. ,vol. 3, pp. 239- 251 ,(1989) , 10.1016/0885-2308(89)90020-X
H. Bourlard, C.J. Wellekens, Links between Markov models and multilayer perceptrons IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 12, pp. 1167- 1178 ,(1990) , 10.1109/34.62605
T. Poggio, F. Girosi, Networks for approximation and learning Proceedings of the IEEE. ,vol. 78, pp. 1481- 1497 ,(1990) , 10.1109/5.58326
N. Morgan, H. Bourlard, Continuous speech recognition using multilayer perceptrons with hidden Markov models International Conference on Acoustics, Speech, and Signal Processing. pp. 413- 416 ,(1990) , 10.1109/ICASSP.1990.115720
Thomas M. Cover, Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition IEEE Transactions on Electronic Computers. ,vol. EC-14, pp. 326- 334 ,(1965) , 10.1109/PGEC.1965.264137
Stephen John Renals, None, Speech and neural network dynamics The University of Edinburgh. ,(1990)
A. Dempster, Maximum likelihood estimation from incomplete data via the EM algorithm Journal of the Royal Statistical Society. ,vol. 39, pp. 1- 38 ,(1977)