© 2014, IJARCSMS All Rights Reserved 31 | P age ISSN: 2321-7782 (Online) Volume 2, Issue 4, April 2014 International Journal of Advance Research in Computer Science and Management Studies Research Article / Paper / Case Study Available online at: www.ijarcsms.com Emotion Recognition Based on MFCC Features using SVM E. Vijayavani 1 Department of Information Technology E. G. S. Pillay Engineering College Nagapattinam, Tamil Nadu – India S.Lavanya 2 Department of Information Technology E. G. S. Pillay Engineering College Nagapattinam, Tamil Nadu – India P. Suganya 3 Department of Information Technology E. G. S. Pillay Engineering College Nagapattinam, Tamil Nadu – India E. Elakiya 4 Department of Computer Science and Engineering E. G. S. Pillay Engineering College Nagapattinam, Tamil Nadu – India Abstract: Music oftentimes referred to as a language of emotion and hence music emotion could be useful in music understanding, retrieval and some other musical related applications. This paper discusses the method to extract features from samples, and using those features, to detect the emotion. we focus on challenging issue of recognizing music emotions such as happy, sad, anger, fear, and neutral. Musical data is collected from various areas. A mel frequency cepstral coefficient (MFCC) is extracted as a feature from the data collected. These features result in different MFCC coefficients that are input to the support vector machine (SVM), which will analyze them with the stored database recognize the emotion. Data are collected from various websites and referred using recorded data. Keywords: Mel Frequency cepstral coefficient, support vector machine, Thayer’s model. I. INTRODUCTION Many issues for music emotion recognition have been addressed by different disciplines such as physiology, psychology, and musicology. In this paper, the challenging issue of recognizing music emotions based on subjective human emotions and acoustic music signal features and present an intelligent music emotion recognition system is focused. Hence, one of the most important prerequisites for realizing such an advanced user interface is a reliable emotion recognition system that guarantees acceptable recognition, robustness, and adaptability to practical applications. To develop such a system requires the following stages: modelling, analysing, processing, training, and classifying emotional features measured from the implicit emotion channels of human communication, such as speech, facial expression, physiological responses, etc. A. Music and Emotion Automatic emotion detection and recognition in speech and music is growing rapidly with the technological advances of digital signal processing and various effective feature extraction methods. Emotion recognition can play an important role in many other potential applications such as music entertainment and human-computer interaction systems. Many researchers have explored models of emotions and factors that give rise to the perception of emotion in music. Many other researchers investigate the problem of automatically recognizing emotion in music. Traditional mood and emotion research in music has focused on finding psychological and physiological factors that influence emotion recognition and classification. During the 1980s, several emotion models were proposed, which were largely based on the dimensional approach for emotion rating. The dimensional approach focuses on identifying emotions of dimensions such as valence and activity. Thayer suggested a two dimensional emotion model that is simple but powerful in organizing different emotion responses. The dimension of stress