Date of Award


Publication Type

Master Thesis

Degree Name



Electrical and Computer Engineering

First Advisor

Kwan, H. K.


Engineering, Electronics and Electrical.




Automatic speech recognition by machine is one of the most efficient methods for man-machine communications. Because speech waveform is nonlinear and variant, speech recognition requires a lot of intelligence and fault tolerance in the pattern recognition algorithms. Fuzzy neural techniques allow effective decisions in the presence of uncertainty. Consequently, the objective of this thesis is to study the fuzzy neural techniques for the application in speech recognition. Two methods are proposed for isolated word recognition using fuzzy pattern matching technique and fuzzy c-means clustering technique. The algorithms are tested based on two LPC-based speech features: line spectrum frequencies and cepstral coefficients. It is shown that the fuzzy algorithm is an efficient approach and can provide reliable and accurate recognition results.Dept. of Electrical and Computer Engineering. Paper copy at Leddy Library: Theses & Major Papers - Basement, West Bldg. / Call Number: Thesis1999 .P56. Source: Masters Abstracts International, Volume: 39-02, page: 0567. Adviser: H. K. Kwan. Thesis (M.A.Sc.)--University of Windsor (Canada), 2000.