AbstractsBusiness Management & Administration

The present day handheld devices such as smart phones IPad etc newlinerequire Internet connection to recognize the spoken word from the dictionary newlinecreated by the speaker and stored in the cloud database This increases the cost newlineand reduces the speed to recognize the speech It cannot work offline The newlineobjective of this work is to overcome this disadvantage and develop a speech newlinerecognition system requiring minimum storage and standalone operation by hand newlineheld devices which is faster requires less memory and gives better accuracy newlineThe field of speech is still open for research as 100 effective system newlineis not yet developed The performance of the system can be measured in terms of newlinethe following metrics newlineAccuracy What is the efficiency of the system in terms of recognition rate newlineMemory What is the total amount of memory required by the system newlineSpeed How fast is the system newlineThere are fundamentally three major reasons why so much research newlineand effort has gone into the problem of trying to teach machines to recognize and newlineunderstand fluent speech and these are the cost reduction new revenue newlineopportunities and customer retention newlineVarious methods for speaker identification and speech recognition are newlinereported in the literature newline newline%%%appendix p160-179, reference p180-165.