LENA recorder IDs autism with 86 percent accuracy

New research suggests that an algorithm based on 12 acoustic parameters associated with vocal development identifies autism in children with 86 percent accuracy.

In late 2009, we wrote about the Language Environment Analysis (LENA) system, which identifies autism in children as young as 18 months by labeling vocalizations from recordings and generating automatic acoustic analysis of those sounds.

The software is not currently Mac compatible. LENA

At the time, LENA claimed its system was 91 percent accurate. Now, according to research published this week in the Proceedings of the National Academy of Sciences, that number has dropped slightly to 86 percent.

The researchers analyzed more than 3 million child utterances from 1,486 all-day recordings of 232 children. Of the 12 acoustic parameters analyzed for vocal development, syllabification (producing well-formed syllables with rapid jaw and tongue movements) proved most telling, according to the research.

Led by D. Kimbrough Oller, professor and chair of excellence in audiology and speech language pathology at the University of Memphis, the researchers describe their findings as a proof of concept that automated analysis of large samples of vocalizations can be included in research on vocal development.

The software processes the DLP data to determine the number of words and conversational turns. LENA

"A small number of studies had previously suggested that children with autism have a markedly different vocal signature, but until now, we have been held back from using this knowledge in clinical applications by the lack of measurement technology," says Steven F. Warren, professor of applied behavioral science at the University of Kansas, who contributed to the study.

The digital language processor fits into the pocket of specially designed clothing and records everything the child vocalizes, but is also able to distinguish from other voices and background sounds.

Since the analysis is of sound patterns, not words, it could potentially screen speakers of any language for autism spectrum disorders, Warren says: "The physics of human speech are the same in all people as far as we know."

The software is not currently Mac compatible. LENA

Warren says that children with autism spectrum disorders can be diagnosed at 18 months, but that the median age in the U.S. is 5.7 years. Early detection could, he adds, improve screening and treatment: "This technology could help pediatricians screen children for ASD to determine if a referral to a specialist for a full diagnosis is required and get those children into earlier and more effective treatments."

The LENA Home kit--which includes LENA Home software, the processor, two items of LENA clothing, two USB cables, a wall charger, and a toy elephant--costs $699. The software is currently not Mac compatible. Also, those who want to listen to the recordings of their children's every moment cannot, due to audio encoding.

About the author

Elizabeth Armstrong Moore is based in Portland, Oregon, and has written for Wired, The Christian Science Monitor, and public radio. Her semi-obscure hobbies include climbing, billiards, board games that take up a lot of space, and piano.

 

Join the discussion

Conversation powered by Livefyre

Don't Miss
Hot Products
Trending on CNET

CNET's Christmas Gift Guide

Under pressure? These will deliver on time

With plenty of top-notch retailers offering digital gifts, you still have time to salvage your gift-giving reputation.