Linguistic and Acoustic Features for Automatic Identification of Autism Spectrum Disorders in Children’s Narrative

Autism spectrum disorders are develop-mental disorders characterised as deficits in social and communication skills, and they affect both verbal and non-verbal communication. Previous works measured differences in children with and without autism spectrum disorders in terms of linguistic and acoustic features, although they do not mention automatic identifi-cation using integration of these features. In this paper, we perform an exploratory study of several language and speech fea-tures of both single utterances and full nar-ratives. We find that there are charac-teristic differences between children with autism spectrum disorders and typical de-velopment with respect to word categories, prosody, and voice quality, and that these differences can be used in automatic clas-sifiers. We also examine the differences between American and Japanese children and find significant differences with re-gards to pauses before new turns and lin-guistic cues.