DocumentCode
423772
Title
A dynamic wavelet neural network for prediction of speech signal
Author
Wang, An-Hong ; Sun, Zhi-Yi ; Li, Zhi-Hong ; Zhang, Xiong
Author_Institution
Dept. of Electron. & Inf., Taiyuan Heavy Machinery Inst., China
Volume
6
fYear
2004
fDate
26-29 Aug. 2004
Firstpage
3524
Abstract
A dynamic wavelet neural network (DWNN) with a feedback is described. Its approximation capacity for learning the long-term dependences between speech signals is also studied. Due to inner-memory, its predictive property is good even if the prediction order (only 3) is low. In the experiments, DWNN performs well and seems to be more promising than RNN and RBF network for speech prediction.
Keywords
neural nets; speech synthesis; wavelet transforms; approximation capacity; dynamic wavelet neural network; speech signal prediction; Machinery; Neural networks; Output feedback; Predictive models; Radial basis function networks; Speech; Sun; Training data; Wavelet analysis; Wavelet transforms;
fLanguage
English
Publisher
ieee
Conference_Titel
Machine Learning and Cybernetics, 2004. Proceedings of 2004 International Conference on
Print_ISBN
0-7803-8403-2
Type
conf
DOI
10.1109/ICMLC.2004.1380400
Filename
1380400
Link To Document