MCFC: A Fuzzy Neural Network Model for Speech Recognition

Article type: Research Article

Authors: Kuo, Yau-Hwang | Hsu, Jang-Pong | Kao, Cheng-I

Affiliations: Institute of Information Engineering, National Cheng Kung University, 1 University Road, Tainan, Taiwan, e-mail: [email protected] and [email protected]

Abstract: A connectionist fuzzy classifier, called CFC, was proposed and shown to perform well in speech recognition. In this article a new learning algorithm with better on-line learning ability and speech recognition performance is developed to replace the original learning algorithm of the CFC model. To distinguish the two learning algorithms, the CFC executing the new learning algorithm is called modified CFC (MCFC). Both of the learning algorithms execute a one-pass learning scheme, which is far faster than the backpropagation-based learning algorithms. In addition, both the CFC and MCFC employ the same four-layered feed forward network structure to implement a “weighted Euclidean distance” fuzzy classification procedure that can be realized by digital hardware with a massively parallel architecture. Some experiments and comparisons for MCFC, CFC, and some other neural network models are also made. The experimental results show that the MCFC has better accuracy and stability for speech recognition than the original CFC, probabilistic neural network, fuzzy ART, and fuzzy ARTMAP, especially in a noisy environment.

DOI: 10.3233/IFS-1996-4402

Journal: Journal of Intelligent and Fuzzy Systems, vol. 4, no. 4, pp. 257-268, 1996