Evaluation of MPEG-7 Descriptors for Speech Emotional Recognition

In this paper we explore the ability of MPEG-7- low level audio descriptors to model the seven emotional categories included in the publically available dataset EmoDB. For our experiments we utilized RBF-SVM classifiers. We made a set of experiments where we examined the seven emotional categories. Experimental results showed that MPEG-7 low-level descriptors (especially a combination of Basic spectral and Timbral features) have the ability to achieve accuracy 77.88% which is comparable to other approaches with high-level perceptual descriptors and to human perception evaluation.