Researchers at the Massachusetts Institute of Technology's (MIT) Computer Science and Artificial Intelligence Laboratory (CSAIL) have used machine learning to develop a computer system that can automatically screen young children for speech and language disorders, and potentially provide specific diagnoses.
The system is designed to analyze audio recordings of children's performances on a standardized storytelling test. MIT professor John Guttag says a tablet or a phone could be used for the storytelling task, and the CSAIL team trained the machine-learning system on identifying speech and language impairments.
Researchers from Massachusetts General Hospital's Institute of Health Professions identified a set of 13 acoustic features of children's speech the machine-learning system could search, and seek patterns that correlate with particular diagnoses.
The researchers say the initial experiments produced promising results.
"I think this opens up the possibility of low-cost screening for large numbers of children, and I think that if we could do that, it would be a great boon to society," Guttag says.
From MIT News
View Full Article
Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA