Emotion in the Speech of Children with Autism Spectrum Conditions: Prosody and Everything Else

Children with Autism Spectrum Conditions (ASC) may experience significant difficulties to recognise and express emotions. The ASC-Inclusion project is setting up an internet-based digital gaming experience that will assist children with ASC to improve their socio-emotional communication skills, combining voice, face, and body gesture analysis, and giving corrective feedback regarding the appropriateness of the child's expressions. The present contribution focuses on the recognition of emotion in speech and on feature analysis. For this purpose, a database of prompted phrases was collected in Hebrew, inducing nine emotions embedded in short-stories. It contains speech of children with ASC and typically developing children under the same conditions. We evaluate the emotion task over the nine categories including the binary valence/arousal discrimination. We further investigate the discrimination of each emotion against neutral. The results show performances for arousal and valance of up to 86.5% and for nine emotions including neutral of up to 42% unweighted average recall. Moreover we compare and analyse manually selected prosodic features with automatic selected features with respect to their relevance for discriminating each of the eight emotion classes.