DSP Based Speech Operated Home Appliances Using Zero Crossing Features

The main idea of this paper is to build a simple speech recognition system using Digital SignalProcessor (DSP) that controls home appliances (i.e. turning on/off) by processing the spokenword. The method used is simple, involving a plain count of the frequency of zero crossings. Twofeatures of zero-crossing are used namely: maxima & running sum that increases the accuracy ofrecognition. The DSP calculates the zero crossings of the spoken words and accordinglygenerates different analog signals at its output. These analog signals are further processed so asto operate the appliances. The words chosen for recognition are ‘ONE’, ‘TWO’ and ‘THREE’.The paper includes two approaches for implementation of speech recognition into DSP, usingMatlab Simulink approach and secondly using Code Composer Studio (CCS). Moreover the firstapproach performs offline processing and the other performs real time processing of words. Theresults at the end describe the efficiency of the system.