Emotion Detection Using Speech Analysis

The functionality to handle the audio file consist of human voice and generate speech, is one of the features which make humans different from other living beings. The human speech can be differentiated by some properties. In this paper we detect the basic emotion of human through speech analysis [1]. As we know that today 95% communication is based on vocals which shows different characteristics of human and emotion is one of them which shows us attribute like fear, anxiety, happiness, sadness and angry etc.[3]. Hence, voice and speech analysis causes emotion inside human and very beneficial in different areas of communication like when a victim has been interviewed, he start stammering if he tells lie and in this case we detect victim's lie with the help of emotion analysis. In politics context we use emotion analysis to detect the emotion of minister at different time laps and get the variety of emotion throughout the speech. Our main objective of this paper is to develop such system which is helpful in near future real time systems and improved human-technology interaction.