This paper investigates the performance of automatic emotional state categorization from speech signals on the Serbian Emotional Speech Corpus, named GEES, against the corresponding human performance. We employ a multistage strategy along with sophisticated features used for automatic emotional state categorization. Our study is the first attempt to apply a machine learning technique to the GEES where the human performance was only available prior to our study. Our investigation indicates that the use of a multistage categorization strategy yields behaviors similar to what human perceives and the performance close to human being's.
Bibliographic reference. Shaukat, Arslan / Chen, Ke (2008): "Towards automatic emotional state categorization from speech signals", In INTERSPEECH-2008, 2771-2774.