Having trouble starting and sustaining a conversation is one aspect of autism spectrum disorder (ASD). “Affecting 1 in 68, ASD is a complex neurodevelopmental disorder characterized by social skill impairments,” according to the Frontiers in Robotics and AI paper.
To help children through this difficulty, a team of researchers have created a Google Glass app called Holli. The software serves as a social coach for children, boxed into user-friendly wearable technology. As users don the wearable tech, the device listens to surrounding conversations and relays appropriate replies.
Technology has been used to help those with ASD in the past, since many are drawn to those devices. However, many existing technologies focus on human-to-computer interactions to teach youngsters social basics. Often times, this technique can have an opposite effect and lead to social isolation.
“The interesting thing about our new technology is that we are not trying to replace human-to-human interactions; instead, we use this app to coach children who are communicating with people in real-world situations,” says Azadeh Kushki, assistant professor at the Institute of Biomaterials and Biomedical Engineering at the University of Toronto, and scientist at the Bloorview Research Institute, Toronto, Canada.
“Children can practice their skills outside of their normal therapy sessions and it can provide them with increased independence in everyday interactions,” Professor Kushki adds.
To test the Holli app, the researchers asked 15 children with ASD to use Holli as a social guide while conducting a conversation. The team found that Holli could complete the majority of conversations without error, and was able to suggest replies before the sentence was finished. This greatly helped to provide a natural flowing discussion.
“Technology has tremendous potential to change the way we think about delivering services to those with ASD. It can augment existing face-to-face interventions to make services accessible in a timely and cost-effective way and help increase treatment effectiveness,” says Professor Kushki.
The team hopes to create custom features specific to a child’s unique needs down the road. A few individualized features include prompt location, medium, and size. Additionally, Holli’s software will be further refined to distinguish differences in speech.
To learn more, read through the full details of the research in the journal Frontiers in Robotics and AI.