COMPARISON OF EFFICIENCY FOR SPEECH RECOGNITION BETWEEN NEURAL NETWORK AND CORRELATION

ABSTRACT In this paper an efficiency of the speech recognition system is compared between the correlation and neural network to recognize Hindi words in MATLAB. This paper takes a brief look at the basic building block of a speech recognition engine. It talks about implementation of different types of modules i.e. Sound Recorder, Framing, Correlation, Feature Extractor and Neural Network Training. In real life, this speech recognition technology might be used in voice calling, call center automation, in data entry, in medical documentation, etc.