This paper extends binary support vector machines to multiclass classification for recognising emotions from speech. We apply two standard schemes (one-versus-one and one-versus rest) and two schemes that form a hierarchy of classifiers each making a distinct binary decision about class membership, on three publicly-available databases. Using the OpenEAR toolkit to extract more than 6000 features per speech sample, we have been able to outperform the state-of-the-art classification methods on all three databases.
Bibliographic reference. Hassan, Ali / Damper, Robert I. (2010): "Multi-class and hierarchical SVMs for emotion recognition", In INTERSPEECH-2010, 2354-2357.