Learning phoneme recognition using neural networks
作者： S. Renals , R. Rohwer
DOI: 10.1109/ICASSP.1989.266453
关键词: Hidden Markov model 、 Recurrent neural network 、 Feature (machine learning) 、 Artificial neural network 、 Pattern recognition 、 Speech recognition 、 Neural gas 、 Artificial intelligence 、 Neocognitron 、 Time delay neural network 、 Computer science 、 Robustness (computer science) 、 Deep learning
摘要: The authors have applied two neural-network models (back-propagation network and radial-basis-functions network) to a static speech recognition problem. offers training times of over orders magnitude faster than back-propagation, when networks similar power generality. computed statistics the with varying numbers hidden units on this back-propagation may offer increased generalization robustness. Both compare favorably vector-quantized Markov model same >
sci-hub.se 参考文章(14)
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)
W. Huang, R. Lippmann, B. Gold, A neural net approach to speech recognition international conference on acoustics speech and signal processing. pp. 99- 102 ,(1988) , 10.1109/ICASSP.1988.196520
John Moody, Chris Darken, Speedy alternatives to back propagation Neural Networks. ,vol. 1, pp. 202- ,(1988) , 10.1016/0893-6080(88)90239-0
A. Crowe, M.A. Jack, Globally optimising formant tracker using generalised centroids Electronics Letters. ,vol. 23, pp. 1019- 1020 ,(1987) , 10.1049/EL:19870714
A. W. F. Huggins, R. S. Nickerson, Speech quality evaluation using "phoneme-specific" sentences. Journal of the Acoustical Society of America. ,vol. 77, pp. 1896- 1906 ,(1985) , 10.1121/1.391941
X.D. Huang, M.A. Jack, Y. Ariki, Parameter re-estimation in semicontinuous hidden Markov modelling of speech with feedback to vector quantisation codebook Electronics Letters. ,vol. 24, pp. 1375- 1377 ,(1988) , 10.1049/EL:19880941
R.W. Prager, F. Fallside, The modified Kanerva model for automatic speech recognition Computer Speech & Language. ,vol. 3, pp. 61- 81 ,(1989) , 10.1016/0885-2308(89)90015-6
S. Renals, R. Rohwer, J. Harrington, M. Terry, A connectionist approach to speech recognition using peripheral auditory modelling international conference on acoustics speech and signal processing. pp. 699- 702 ,(1988) , 10.1109/ICASSP.1988.196682
A. Waibel, T. Hanazawa, G. Hinton, K. Shikano, K. Lang, Phoneme recognition: neural networks vs. hidden Markov models vs. hidden Markov models international conference on acoustics speech and signal processing. pp. 107- 110 ,(1988) , 10.1109/ICASSP.1988.196523