Title :
Window structure and computation of neural networks for speech recognition
Author :
Zhang, D. ; Elmasry, M.I.
Author_Institution :
Dept. of Electr. & Comput. Eng., Waterloo Univ., Ont., Canada
fDate :
27 Jun-2 Jul 1994
Abstract :
Neural networks (NNs), as processors of time-sequence patterns, have been successfully applied to several speaker dependent speech recognition systems. They can be efficiently implemented by a pipelined architecture. In this paper, the authors explore its window structure as a computation component in the architecture. Two types of windows, parallel and serial data flow window, and their computation units with both feedforward and feedback paths are developed. The implementations of the windows are easily matched to the VLSI medium. Examples of applications to the NNs and performance analysis are given to illustrate effectiveness of the proposed window computation
Keywords :
data flow computing; neural nets; speech recognition; feedback; feedforward; neural networks; parallel data flow window; pipelined architecture; serial data flow window; speaker dependent speech recognition systems; speech recognition; time-sequence patterns; window structure; Computer architecture; Computer networks; Delay; Multi-layer neural network; Neural networks; Performance analysis; Pipelines; Speech recognition; Very large scale integration; Windows;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374993
