Isolated Word Speech Recognition Using Fuzzy Neural TechniquesPOMPES PAR TRANSITIONS MULTIPLES

منو

" Isolated Word Speech Recognition Using Fuzzy Neural TechniquesPOMPES PAR TRANSITIONS MULTIPLES "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	152341
Doc. No	:	ET24133
Main Entry	:	Hui Ping
Title Proper	:	Isolated Word Speech Recognition Using Fuzzy Neural TechniquesPOMPES PAR TRANSITIONS MULTIPLES
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	Automatic speech recognition by machine is one of the most efficient methods for man-machine communications. Because speech waveform is nonlinear and variant. speechrecognition requires a lot of intelligence and fault tolerance in the pattern recognitionalgorithms. Fuzzy neural techniques allow etliective decisions in the presence ofuncct intr-. Consequently. the objective of this thesis is to study the fuuy neural techniques['or the application in speech recognition. Two methods are proposed for isolated wordrecognition using fuzzy pattern matching technique and Fuzzy c-means clustering technique.I'hs algorithms are tested based on t~vo LPC-based speech features: line spectrumfrcqusncies and cepstral cost'ficients. It is shown that the fuzzy algorithm is an efficientapproach and can provide reliable and accurate recognition results..
Subject	:	Electericl tess
	:	برق
electronic file name	:	TL48335.pdf
Title and statement of responsibility and	:	Isolated Word Speech Recognition Using Fuzzy Neural TechniquesPOMPES PAR TRANSITIONS MULTIPLES [Thesis]