Speech recognition approach: Desktop items activation with comparative analysis

Abstract

Advances in speech technology and computing power have created a surge of interest in the practical application of speech recognition. The main goal of this paper is to facilitate recognition accuracy, with emphasis on acoustic and language modeling. With the recognition of speech commands generation of the commands for desktop items activation. Practical speech recognition also requires the computation to be carried out in real time within the limited resources i.e CPU power and memory size of commonly available computers. In this paper we focus on implementing dynamic time warping algorithm and compare the results with viterbi search algorithm so that speech recognition systems that are insensitive to the constraints in the speech signal and attain human like recognition performance can be identified and can be used for commercial use.