A dynamic neural network for syllable recognition
作者： Lin Zhong , Yuanyuan Shi , Runsheng Liu
DOI: 10.1109/IJCNN.1999.836002
关键词:
摘要: A dynamic neural network architecture based on the time-delay and convolutional is originated. The achieves much better performance than those of MLP TDNN when dealing with syllable recognition. Such also comparable to that more popular HMM method.
rice.edu参考文章(6)
Yumin Lee, Lin-shan Lee, Continuous hidden Markov models integrating transitional and instantaneous features for Mandarin syllable recognition Computer Speech & Language. ,vol. 7, pp. 247- 263 ,(1993) , 10.1006/CSLA.1993.1013
A. Waibel, H. Sawai, K. Shikano, Modularity and scaling in large phonemic neural networks IEEE Transactions on Acoustics, Speech, and Signal Processing. ,vol. 37, pp. 1888- 1898 ,(1989) , 10.1109/29.45535
Kevin J. Lang, Alex H. Waibel, Geoffrey E. Hinton, A time-delay neural network architecture for isolated word recognition Neural Networks. ,vol. 3, pp. 23- 43 ,(1990) , 10.1016/0893-6080(90)90044-L
Gee-Swee Poo, Large vocabulary Mandarin Final recognition based on two-level time-delay neural networks Speech Communication. ,vol. 22, pp. 17- 24 ,(1997) , 10.1016/S0167-6393(97)00013-7
A. Waibel, T. Hanazawa, G. Hinton, K. Shikano, K.J. Lang, Phoneme recognition using time-delay neural networks IEEE Transactions on Acoustics, Speech, and Signal Processing. ,vol. 37, pp. 393- 404 ,(1989) , 10.1109/29.21701
Y. Le Cun, L.D. Jackel, B. Boser, J.S. Denker, H.P. Graf, I. Guyon, D. Henderson, R.E. Howard, W. Hubbard, Handwritten digit recognition: applications of neural network chips and automatic learning IEEE Communications Magazine. ,vol. 27, pp. 41- 46 ,(1989) , 10.1109/35.41400