Syracuse Sun

On August 16, 2024, it was announced that Jonathan Preston, a professor in the Department of Communication Sciences and Disorders at the College of Arts and Sciences, is part of a team awarded a grant from the National Institutes of Health (NIH). The grant will fund research into biofeedback technologies for speech therapy.

One common speech error in English involves substituting a “w” sound for an “r” sound. While most children outgrow such errors, 2% to 5% exhibit residual speech sound disorder into adolescence. Research indicates that biofeedback technologies can assist children struggling with the “r” sound by making the sound visible.

Biofeedback speech therapies employ electronics to display real-time representations of speech that children cannot ordinarily perceive on their own. In this method, children see what an “r” sound looks like on a screen while hearing their own pronunciation. A visual model representing the correct pronunciation provides a target for adjustment.

Preston and scientists from New York University and Montclair State University will compare these technologies' effectiveness under different conditions. They will also evaluate AI-based tools designed to guide home-based practice with human oversight.

“If we want kids to improve quickly, we’d want them to practice at home,” Preston says. “But they don’t have a skilled speech pathologist available at home to help them practice.”

Many children lack access to clinicians who use biofeedback methods. AI could potentially change this scenario. The research team has trained an AI-powered speech therapy algorithm using voices from over 400 children.

“At home, kids will talk into a microphone, and based on the algorithm, the child will receive feedback about whether they spoke the word clearly or not,” says Preston.

Further details about the grant are available on the College of Arts and Sciences’ website.

Story by John H. Tibbetts