Speech Recognition and Emotion Sensor System

Abstract

Speech is a basic unit for communication or humans. In this decade computer technology is drastically evolving. In this regard, review of existing work on emotional speech processing is useful for carrying out further research. So to make communication easier between human and computer, Speech Recognition provides a great role. Speech recognition is a technique in which a human speaks to computer in his/her comfortable language and computer is such an intelligent to understand his/her spoken words and respond accordingly. Currently there are number of systems which meet this domain of speech recognition and emotion detection. Keeping in mind these constraints we are trying to develop a system which cannot only resolve these issues but also provide simple and usable interface to public as well. We are aiming to provide some basic professional modules on one platform which are Speech Recognition, Emotion Prediction and separating two Classes of any voice input. Our system shall be a good example of proving credibility of voice signature as it shall offer a very unique service which is very rarely offered in public domain. It shall be able to separate multiple voices which are enclosed in one audio signal. This means we can hear our chosen voice at one time. Speaking style classification is improved by using the modulation spectrum in combination with standard pitch and frequency variation.