top of page

Using machine learning technology to drive the future of autism diagnoses

Currently seeking vocal samples and recordings from families with autistic children for our NSF-funded study dedicated to improving access to early interventions for autism care.

What is EASI-AS?

Our Evaluative Artificial Speech Intelligence-Autism Screener project (EASI-AS) is an NSF/SBIR Phase II grant. EASI-AS will feature cutting-edge machine-learning technology that will reliably screen for autism by identifying non-linguistic acoustic features, extracted from recordings of children’s speech. The system will use familiar mobile devices to collect speech samples, which will employ a user-friendly interface that parents and professions can operate with little to no training. Research has shown that early intensive intervention services can improve social and communication skills in autistic children. So increasing access to early intervention services is one of the key goals of our project.​

How can our community get involved?

We are working to help autistic children and their families by creating a tool that anonymously screens for autism by using speech samples. We are currently seeking language samples.
Frame 113 (2).png

Steps for creating a language sample

Group 109 (1).png
Engage your child in a game where they can verbalize what they’re doing or have questions prepared to ask about your child’s school day or favorite things to do.
Group 110 (1).png
Record using your phone or an online recording platform to create a 30 sec - 2 minute language sample.
Group 111 (1).png
Save as a .wav file and upload below. We are currently accepting vocal samples from children with and without autism. You will be asked to fill out a volunteer form and confirm you understand how the data will be used securely. If you have any questions, please reach us here.
Click to Participate

Get In Touch

If you would like to contribute recordings to the project, please click here. If you have any questions about EASI-AS and our Phase II SBIR work, please contact us at

bottom of page