摘要：There are two problems when conditional T-S fuzzy Neural network is used directly in speech recognition system. One is the rule disaster problem, that is, the rule number will increase exponentially with the increase of input dimensions. Another problem is the network reasoning failure resulted from input dimensions too large. The paper presented an improved algorithm of T-S fuzzy neural network. The subtraction clustering algorithm was used to make certain rule number to escape the rule disaster. The network reasoning can correctly work by adding a compensated factor on membership. The improved algorithm was used in speech recognition system. The experimental results showed that the recognition results of improved algorithm are better than the ones of radial basis function (RBF) neural network using Kmeans clustering algorithm to select the centroid. And it has much better robustness.
