Regular PapersNo Access

SPEAKER-INDEPENDENT SPEECH RECOGNITION BASED ON FAST NEURAL NETWORK

CUI TAO

Department of Information and Communication Engineering, Xian Jiaotong University, Xian, 710049, P.R.China

Search for more papers by this author

and

TAIYI ZHANG

Department of Information and Communication Engineering, Xian Jiaotong University, Xian, 710049, P.R.China

Search for more papers by this author

https://doi.org/10.1142/S0218213003001320Cited by:1 (Source: Crossref)

Abstract

This paper presents a fast Neural Network algorithm, in which the step is regarded as the function of the error and the output function of network node, and weight is calculated by different step. By adopting the fast NN algorithm, we developed a speaker-independent speech recognition system. The experiment shows that the new algorithm is over 10 times faster than the traditional BP algorithm and has better performance and spreading ability.

Keywords:

Remember to check out the Most Cited Articles!
Check out Notable Titles in Artificial Intelligence.

References

J. B. Hampshire and A. H. Waibel, IEEE Trans. on Neural Networks 1(2), 216 (1990). Crossref, Google Scholar
P. Burrascano and P. Lucci, Smoothing backpropagation cost function by delta constraining, Proc. of Int. Joint Conf. on Neural Network, June, 1990 . Google Scholar
S. Davis and P. Mermelstein, IEEE Trans. on Acoustics, Speech, and Signal Processing 28(4), 357 (1980). Crossref, Google Scholar
A. H. Wailbel , Neural Networks Approaches for Speech Recognition ( Ed: Prentice-Hall , 1991 ) . Google Scholar
A. Ugena, F. de Arriaga and M. El Alami, Speaker-independent speech recognition by means of functional-link neural networks, Proc. Of IEEE Internat. Conf. Pattern Recognition, 1018-1021, 2000 . Google Scholar