Abstract
In medical research, autism spectrum disorder (ASD) is known as having social problems such as social interaction deficit, difficulties of communication, and repetitive behavior. Especially for the children, people with ASD have difficulties on dealing with verbal and non-verbal cues in social interaction. Some research indicate that embodied conversational agents (ECA) is helpful for improving social capabilities, or communication skills. In the case of autism, ECA is often used to solve the general problem in children with autism. For example, it can be used to elicit the natural behavioral performance of the autism patients, including verbal, emotion recognition, or body movement. To evaluate the syndrome in autism spectrum, a gold standard diagnostic tools-Autism diagnostic observation schedule (ADOS) is used to assess the severity of autism in clinical assessment of ASD. ADOS is usually conducted by professionals that are familiar with autistic disorders, and it measures social impairments in three core developmental domains: communication, reciprocal social interaction, communication and social. However, because there are existing problems like subjective evaluation, time-consuming, and non-scalable in manually assessment method, most of the information cannot be effectively utilized. Therefore, in this paper, we design an automatic assessment system based on behavior-based measurement to provide an early diagnosis with using ECA, and realize an automation autism diagnostic framework by behavioral signal processing (BSP) technique which consists of low-level multimodal signal feature, mid-level behavior feature, and high-level ADOS score. In the future, we expect to provide more convenient diagnostic tools to experts with decision-making objective reference and improve people's daily lives.