Speech signal prediction using feedforward neural network

被引:7
作者
Chu, WC [1 ]
Bose, NK [1 ]
机构
[1] Penn State Univ, Spatial & Temporal Signal Proc Ctr, Dept Elect Engn, University Pk, PA 16802 USA
关键词
D O I
10.1049/el:19980658
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The conflicting factors of performance and efficiency in a nonlinear predictor of speech signals based on the feedforward multilayer perceptron with one hidden layer are evaluated for various combinations of the number of input and hidden units.
引用
收藏
页码:999 / 1001
页数:3
相关论文
共 7 条
[1]  
AGAROFOLO J, 1993, DARPA TIMIT ACOUSTIC
[2]  
Bose N.K., 1996, Neural Network Fundamentals with Graphs, Algorithms, and Applications
[3]  
DIAZDEMARIA F, 1995, INT CONF ACOUST SPEE, P788, DOI 10.1109/ICASSP.1995.479812
[4]  
Kleijn W. B., 1995, Speech Coding and Synthesis
[5]  
Rabiner LR., 1978, DIGITAL PROCESSING S
[6]  
THYSSEN J, 1994, IEEE ICAASSP, V1, P185
[7]  
Tong H., 1990, NONLINEAR TIME SERIE