Title :
The use of fuzzy membership in network training for isolated word recognition
Author :
Qi, Yingyong ; Hunt, Bobby R. ; Bi, Ning
Author_Institution :
Arizona Univ., Tucson, AZ, USA
Abstract :
A modification to the use of fuzzy membership in the training of an artificial neural network is presented. The modified membership function can be applied to patterns that have a multi-center data structure in the feature space, and is used in network training for isolated word recognition. The results indicate that the network trained using this fuzzy membership function has a better overall recognition rate than either the network trained by the conventional error backpropagation method or the classifier derived from vector quantization
Keywords :
data structures; fuzzy set theory; learning (artificial intelligence); neural nets; speech recognition; feature space; fuzzy membership; fuzzy set theory; isolated word recognition; learning; multi-center data structure; neural network; speech recognition; Auditory system; Bismuth; Data structures; Fuzzy neural networks; Fuzzy sets; Intelligent networks; Neural networks; Pattern classification; Pattern recognition; Speech recognition;
Conference_Titel :
Neural Networks, 1993., IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0999-5
DOI :
10.1109/ICNN.1993.298834
