Abstract
Autism spectrum disorder (ASD) is a developmental disorder characterized by impairment in social communication, restricted interest and stereotyped behaviors. Since current diagnosis methods are depending on time intensive subjective assessments, the establishment of novel therapeutics could be facilitated by objective, quantitative, and reproducible methods for supporting diagnosis. To that end, we investigated acoustic features of speech which characterize the difference between ASD and typical development (TD). The focus of this paper are features related to fillers and laughter, which play important roles in communication as social signals, and were observed to be used differently by ASD and TD individuals in previous research. We investigated several such features and statistically evaluated how helpful they are for discriminating between ASD and TD. In an experiment, we applied a support vector machine (SVM) for ASD classification considering both prosodic acoustic features as well as the most significant features related to social signals. Discrimination accuracy and F-measure of were slightly improved when using not only the prosodic features but also those related to social signals.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.