Hardware implementation of voice operated robot using Support Vector Machine classifier

Abstract

Many consumer and industrial applications require fast and lightweight real-time speech recognition systems with limited vocabulary, such as hands-free control for portable music players, car audio systems, cordless phones, wheel chairs, washing machines, micro-wave ovens, air conditioners and domestic appliances. In this paper, design and development of a Texas Instruments TMS320C6713 DSP based real-time voice operated robot using Support Vector Machine (SVM) classifier is proposed. Details about different ways to reduce the execution time of the prototype are reported in this paper. The proposed system as well as approaches can be easily employed by designers for various other SVM based multi-class pattern recognition applications.