IMPLEMENTATION OF SPEECH RECOGNITION SYSTEM

The aim of this paper is to express the accuracy and time results of speech recognition (SR) system, based on Mel-Frequency Cepstral Coefficients (MFCC). The numbers of speech files were considered for the experimentation, MFCC were extracted and coefficients were statistically analyzed. Audio database is used for training and testing of the algorithm. Also Gaussian filters have been replaced with triangular filters to achieve higher level of accuracy. The speech files of about 2 second duration are to be given as input to training and testing unit. The results will be checked for a number of speech files. The accuracy achieved by the proposed approach is expected higher than previous systems under study and can be implemented using Matlab as the programming tool