STOCHASTIC MODELING BASED SPEECH RECOGNITION USING MFCC

Abstract

The aim is to recognize, compare, newlineclassify and identify with the help of computation and applied techniques. To perform newlinethe task of classification of noise sources, LPC and MFCC were used as input to the newlineclassifiers in experimental work. LDA, QDA and ANN are tested for the classification newlinepurpose. Once the source is identified we can address these untoward noisiness class newlineand to minimize their impact to the human perceptions through the implementation of newlineappropriate technique/devices to enhance the system recognition efficiency. The newlineperformance of LDA, QDA and ANN with LPC and MFCC is analyzed. It is evident that newlineANN in combination with MFCC gives the best result and showing efficiency about newline90%. newline