Fuzzy neural networks for speech endpoint detection
Gin-Der Wu, Zhenwei Zhu, An-Tai Li · 2012
This paper proposes fuzzy neural networks (FNN) for speech endpoint detection. The underlying notion of the proposed FNN is to split the generation of fuzzy rules into linear discriminant analysis (LDA) and Gaussian mixture model (GMM). In LDA, the weights are updated by seeking directions that are efficient for discrimination. In GMM, the parameter learning adopts the gradient descent method to reduce the cost function. Since LDA-based fuzzy rules can efficiently increase the discriminative capability among different classes, the proposed FNN can classify highly confusable patterns.