Emotion Based Information Retrieval System

Abstract

Abstract—Music emotion plays an important role in music retrieval, mood detection and other music-related applications. Many issues for music emotion recognition have been addressed by different disciplines such as physiology, psychology, cognitive science and musicology. We present a support vector regression (SVR) based Music Information Retrieval System (Emotion based). We have chosen the “Raga” paradigm of Indian classical music as the basis of our formal model since it is well understood and semi-formal in nature. Also a lot of work has been done on Western Music and Karnataka classical Music Initially in the system features are extracted from music. These features are mapped into emotion categories on the Tellegen-Watson Clark model of mood which is an extension to the Thayer’s two-dimensional emotion model. Two regression functions are trained using SVR and then distance and angle values are predicted A categorical Response Graph is generated in this module which shows the variation of emotion .