Design A Dependent Voice Commands Selective System

Abstract

Voice commands recognition is a way of understanding human speech and converting it to a communication input of computer. Based on the data used to feed the voice recognition system, systems could be classified as dependent or independent systems. In this paper, a dependent voice commands selective system is presented. The system uses the spectral subtraction algorithm for noise cancellation. A new algorithm is named Select Matching Command Algorithm SMCA is used for matching voice command identification. Six different users (3 male and 3 female) are used to test the system. Each user tests the system two times, one by using twenty four voice commands samples previously selected and other time by using another twenty four voice commands out of the twenty four preselected samples. The proposed system is able to correctly identify the matching voice commands 90.97% of the time when testing the system with the predefined voice commands. Testing the system with voice commands out of the predefined commands shows 92.36 % of no matching identification. According to the results noted from the six users, overall percent of selective accuracy of the suggested system is 91.67 %.