In this paper, the authors describe a support vector machine is a 5-10 words each is collected under acoustically controlled room is taken. MFCC are extracted from speech signal of promising machine learning technique that has generated a lot of interest in the pattern recognition. It is an approach of isolated speech recognition by digital signal processor TMS620C6713 using mel scale frequency cepstral coefficients and euclidean distance or support vector machine. Several features are extracted from speech signal of spoken words. An experiments database of total five speakers, speaking spoken words.