Title :
Speech classification using a modified focused gamma network
Author :
Kuo, Jyh-Ming ; Ipe, Jose C Princ
Author_Institution :
Dept. of Electron. Eng., Kaohsiung Polytech. Inst., Taiwan
Abstract :
A modified version of the focused gamma network is proposed and applied to speech classification. Each input neuron of the network is equipped with a pair of gamma memories which have an adjustable time-scale parameter. In addition, each channel of speech features is equally divided into several segments, and each segment is clocked into an individual input neuron. With these modifications, the network is able to develop a proper time scale for each segment of patterns and handle speech patterns of different lengths as well
Keywords :
filtering theory; multilayer perceptrons; network topology; pattern classification; speech recognition; focused gamma network; gamma filter; gamma memory; input neuron; multilayer perceptron; network topology; neural networks; speech classification; speech recognition; time-scale parameter; Clocks; Convergence; Delay lines; Filters; Multilayer perceptrons; Neural networks; Neurons; Speech processing; Speech recognition;
Conference_Titel :
Neural Networks, 1996., IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-3210-5
DOI :
10.1109/ICNN.1996.549187
