Apparatus for calculating a posterior probability of phoneme symbol, and speech recognition apparatus
作者： Toshiaki Fukada , Mike Schuster
DOI:
关键词: A priori and a posteriori 、 Signal 、 Speech recognition 、 Posterior probability 、 Layer (object-oriented design) 、 Character (computing) 、 Symbol (chemistry) 、 Feature (machine learning) 、 Recurrent neural network 、 Computer science
摘要: There are disclosed an apparatus for calculating a posteriori probabilities of phoneme symbols and speech recognition using the symbols. A feature extracting section extracts parameters from signal uttered sentence composed inputted character series, calculates probability symbol signal, by bidirectional recurrent neural network. The network includes (a) input layer receiving extracted means plurality hypothetical series signals, (b) intermediate at least one having units, (c) output outputting each symbol. first neuron group forward module, backward module.
lens.org 参考文章(10)
Victor Abrash, Mixture Input Transformations for Adaptation of Hybrid Connectionist Speech Recognizes conference of the international speech communication association. ,(1997)
Candace A. Kamm, Robert B. Allen, S. B. James, A recurrent neural network for word identification from phoneme sequences. conference of the international speech communication association. ,(1990)
Masahiro Matsuoka, Mostefa Golea, Time-series trend estimating system and method using column-structured recurrent neural network ,(1996)
M. Schuster, Learning out of time series with an extended recurrent neural network Neural Networks for Signal Processing VI. Proceedings of the 1996 IEEE Signal Processing Society Workshop. pp. 170- 179 ,(1996) , 10.1109/NNSP.1996.548347
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
A.J. Robinson, An application of recurrent nets to phone probability estimation IEEE Transactions on Neural Networks. ,vol. 5, pp. 298- 305 ,(1994) , 10.1109/72.279192
M. Schuster, K.K. Paliwal, Bidirectional recurrent neural networks IEEE Transactions on Signal Processing. ,vol. 45, pp. 2673- 2681 ,(1997) , 10.1109/78.650093
H. Bourlard, N. Morgan, Continuous speech recognition by connectionist statistical methods IEEE Transactions on Neural Networks. ,vol. 4, pp. 893- 909 ,(1993) , 10.1109/72.286885
James T. Lo, Optimal filtering by recurrent neural networks ,(1993)
Volker Tresp, Learning method for a neural network ,(1996)