Investigation of Classification Using Pitch Features for Children with Autism Spectrum Disorders and Typically Developing Children

Abstract

Recently, autistic spectrum disorders (ASD) have been the focus of much research. Anautistic spectrum disorder is a congenital cerebral dysfunction, and it is a type of developmental disease that causes difficulties incommunication, perceptual, cognitive, and linguistic functions. Since the symptoms of an autistic spectrum disorder are the result of a variety of causes, a fundamental, all-encompassing medical treatment is difficult. However, for an autistic spectrum disorder, early detection and suitable education can have a significant impact on future social prognosis. In this paper, for the purpose of early-age detection of ASD, an investigation of classification using pitch features is carried out for children with autism spectrum disorders and typically developing children, where statistics (percentiles, moment, maximum, minimum, and range) for static and dynamic pitch features are used for classification. Experimental results show 1) that a section division (the head, middle, and tail sections) of an utterance provides a better accuracy, compared with no section divisions of an utterance, and 2) the section that contributed to the classification of ASD was the head section of the utterance.