Title :
Analysis of spectral feature extraction using the gamma filter
Author :
Çelebi, Samel ; Principe, Jose C.
Author_Institution :
Computational Neuroeng. Lab. CSE447, Florida Univ., Gainesville, FL, USA
fDate :
27 Jun-2 Jul 1994
Abstract :
Studies the focused gamma network and its special case, the time delay neural net, for speech recognition from a signal representation point of view and show that these structures extract the features of the signals input to them in the form of Taylor´s series approximation performed in the frequency domain
Keywords :
Laplace transforms; feature extraction; neural nets; pattern classification; series (mathematics); signal representation; speech recognition; Taylor´s series approximation; focused gamma network; frequency domain; gamma filter; signal representation; spectral feature extraction; speech recognition; time delay neural net; Artificial neural networks; Band pass filters; Feature extraction; Frequency; IIR filters; Laplace equations; Neural networks; Spectral analysis; Speech recognition; Taylor series;
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.1994.374997
