A COMBINED SELF-ORGANIZING FEATURE MAP AND MULTILAYER PERCEPTRON FOR ISOLATED WORD RECOGNITION

This paper presents a neural network system which combines a self-organizing feature map and multilayer perception for the problem of isolated word speech recognition. A new method combining self-organization learning and K-means clustering is used for the training of the feature map, and an efficient adaptive nearby-search coding method is designed based on the "locality" of the self-organization, which has been shown to save about 50% computation without degradation in recognition rate compared to the full-search coding. Various experiments for different choices of parameters in the system were conducted on the TI 20 word data base with best recognition rates as high as 99.5% for both speaker-dependent and multispeaker-dependent tests.