Voice Emotion Games: Language and Emotion in the Voice of Children with Autism Spectrum Condition

Three decades of research have shown that children and adults with Autism Spectrum Conditions (ASC) may experience significant difficulties recognizing and expressing emotions and mental states. These difficulties are apparent when individuals with ASC attempt to recognize emotions from facial expressions, from vocal intonation, from gestures and body language. This ASC-Inclusion project set up advanced ICTenabled solutions and serious games that 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 childs expressions. The present contribution focuses on the recognition of emotion in speech. For this purpose, a database of prompted phrases was collected in English, Swedish, and 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, by investigating the discrimination of each emotion against the remaining ones. The results show performances up to 83.8 % unweighted average recall.