Toddlers With Autism Pronounce Words Differently
A new automated vocal analysis system has found that autistic toddlers pronounce words differently than their health peers. The researchers hope the technology could help pediatricians screen children for ASD so they can receive earlier and more effective treatment.
Researchers from Kansas University used a device called LENA, or Language Environment Analysis, which works by recording a child’s speech for a day and then feeds the data into a special computer program that compares the early speech noises with those of other children known to have autism spectrum disorder. The device is small enough to fit into a pocket of specially designed children’s clothing.
The study included 1,486 recordings from 232 children aged between 10 months and four years. Recordings were made by the parents at home and in other natural environments. The 3.1 million different identified utterances were then passed through a computer-based algorithm based on the 12 acoustic parameters associated with vocal development. The system picked up those with autism with 86% accuracy.
The early speech of infants with autism, particularly the way they pronounce the syllables of words, are distinct from those of typically developing children. It also identified cases of language development delay.
Early diagnosis and treatment of autism can have a dramatic effect on the development of children, said Professor Steven Warren, professor of applied behavioral science at UK. Identifying children early can lead to a faster referral to a specialist for a full diagnosis and individualized treatments.
Warren says that children with autism spectrum disorders can be diagnosed at 18 months but that the median age of diagnosis is 5.7 years in the United States.
The study was reported in the July 19 online Proceedings of the National Academy of Sciences