Thumbnail
Access Restriction
Subscribed

Author Zhang, D.D.
Source IEEE Xplore Digital Library
Content type Text
Publisher Institute of Electrical and Electronics Engineers, Inc. (IEEE)
File Format PDF
Copyright Year ©1996
Language English
Subject Domain (in DDC) Technology ♦ Engineering & allied operations
Subject Keyword Nonhomogeneous media ♦ Neural networks ♦ Speech recognition ♦ Computer architecture ♦ Windows ♦ Performance analysis ♦ Delay ♦ Pipelines ♦ Computer science ♦ Speech processing
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, we 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.
Description Author affiliation: Dept. of Comput. Sci, City Univ. of Hong Kong, Kowloon, Hong Kong (Zhang, D.D.)
ISBN 0780332806
ISSN 1062922X
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research ♦ Reading
Education Level UG and PG
Learning Resource Type Article
Publisher Date 1996-10-14
Publisher Place China
Rights Holder Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Size (in Bytes) 396.09 kB
Page Count 5
Starting Page 725
Ending Page 729


Source: IEEE Xplore Digital Library