Fundamental factor in communication of humans is nothing but Emotions. It would be ideal to have human emotions automatically recognized by machines, mainly for improving human machine interaction. Most of work in field of emotion recognition is done using recorded or offline database. Very selective research work is carried in real time high performance emotion recognition. In application of human computer interaction Real-time high performance emotion recognition is necessary for analyzing and responding to the user's emotions while he or she is interacting with an application. The proper choices of features and classifiers are important for a real-time high performance emotion recognition system. In this paper real time emotion recognition system is proposed, which extracts the emotions from real time speech based on extracting prosody, quality and dynamic features, classification of emotions using Multidimensional SVM and testing real time speech samples with training databases with emotional speech in 'Native Marathi' language has been presented

1. K. S. Rao, S. G. Koolagudi, and R. R. Vempada, "Emotion recognition from speech using global and local prosodic features," Int. J. Speech Technol. , vol. 16, no. 2, pp. 143–160, Aug. 2012.
2. D. Ververidis and C. Kotropoulos, "Emotional speech recognition: Resources, features, and methods," Speech Commun. , vol. 48, no. 9, pp. 1162–1181, Sep. 2006.
3. I. Luengo and E. Navas, "Automatic Emotion Recognition using Prosodic Parameters" pp. 493–496, 2005.
4. C. M. Lee, S. Member, S. S. Narayanan, and S. Member, "Toward Detecting Emotions in Spoken Dialogs," vol. 13, no. 2, pp. 293–303, 2005.
5. M. Borchert and a. Dusterhoft, "Emotions in speech - experiments with prosody and quality features in speech for use in categorical and dimensional emotion recognition environments," 2005 Int. Conf. Nat. Lang. Process. Knowl. Eng. , vol. 00, pp. 147–151, 2005.
6. S. Wu, H. Tiago"Automatic Recognition Of Speech Emotion Using Long-Term Spectro-Temporal Features," 2009.
7. A. B. Kandali, S. Member, A. Routray, and T. K. Basu, "Emotion recognition from Assamese speeches using MFCC features and GMM classifier. "
8. Y. Pan, P. Shen, and L. Shen, "Speech Emotion Recognition Using Support Vector Machine," vol. 6, no. 2, pp. 101–108, 2012.
9. M. Dumas, "Emotional Expression Recognition using Support Vector Machines. "
10. P. Shen and X. Chen, "Automatic Speech Emotion Recognition Using Support Vector Machine," pp. 621–625, 2011.
11. D. Fradkin and I. Muchnik, "Support Vector Machines for Classification," vol. 0000, pp. 1–9, 2006.
12. A. Hassan and R. I. Damper, "Multi-class and hierarchical SVMs for emotion recognition. "
13. N. Yang, R. Muraleedharan, J. Kohl, I. Demirkol, and W. Heinzelman, "Speech-based Emotion Classification using Multiclass SVM with Hybrid Kernel and Thresholding Fusion" pp. 455–460, 2012

Mfcc Prosody Features Quality Features Speech Emotion Recognition Support Vector Machine