Probability estimation by feed-forward networks in continuous speech recognition
作者： S. Renals , N. Morgan , H. Bourlard
关键词:
摘要: The authors review the use of feedforward neural networks as estimators probability densities in hidden Markov modelling. In this paper, they are mostly concerned with radial basis functions (RBF) networks. They not isomorphism RBF to tied mixture density estimators; additionally note that trained estimate posteriors rather than likelihoods estimated by estimators. show how network training should be modified resolve mismatch. also discuss problems discriminative training, particularly problem dealing unlabelled data and mismatch between model priors. >
ed.ac.uk
sci-hub.se 参考文章(13)
David Lowe, David S. Broomhead, Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks Complex Systems. ,vol. 2, pp. 321- 355 ,(1988)
M. J. D. Powell, Radial basis functions for multivariable interpolation: a review Algorithms for approximation. pp. 143- 167 ,(1987)
L. Bahl, P. Brown, P. de Souza, R. Mercer, Maximum mutual information estimation of hidden Markov model parameters for speech recognition international conference on acoustics, speech, and signal processing. ,vol. 11, pp. 49- 52 ,(1986) , 10.1109/ICASSP.1986.1169179
Lalit R. Bahl, Frederick Jelinek, Robert L. Mercer, A Maximum Likelihood Approach to Continuous Speech Recognition IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. PAMI-5, pp. 179- 190 ,(1983) , 10.1109/TPAMI.1983.4767370
John S. Bridle, Alpha-nets: a recurrent “neural” network architecture with a hidden Markov model interpretation Speech Communication. ,vol. 9, pp. 83- 92 ,(1990) , 10.1016/0167-6393(90)90049-F
J.S. Bridle, L. Dodd, An Alphanet approach to optimising input transformations for continuous speech recognition international conference on acoustics, speech, and signal processing. pp. 277- 280 ,(1991) , 10.1109/ICASSP.1991.150331
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
S. Renals, D. McKelvie, F. McInnes, A comparative study of continuous speech recognition using neural networks and hidden Markov models international conference on acoustics, speech, and signal processing. pp. 369- 372 ,(1991) , 10.1109/ICASSP.1991.150353
Hervé Bourlard, Nelson Morgan, A Continuous Speech Recognition System Embedding MLP into HMM neural information processing systems. ,vol. 2, pp. 186- 193 ,(1989)
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