Listening to the noises an infant makes can identify autism and allow for earlier and more effective treatments, scientists say.

A study published in the journal Proceedings of the National Academy of Sciences found that autistic children have different speech patterns from children without the condition.

In one example, autistic children show slow development in syllables such as “ba,” explains lead author Kimbrough Oller. The deviation in autistic children can be identified by using automated vocal analysis technology to listen to voice recordings, Dr. Oller and his colleagues say.

The researchers analyzed voice recordings of 232 children aged 10 months to four years. Out of the 1,500 day-long vocal soundtracks, more than 3 million individual child utterances were used in the research. When 12 specific sound parameters associated with the vocal development were examined, the researchers found that there is a ‘robust difference’ between autistic children and children without the condition.

The research proves, says Dr. Oller, that speech and voice do have a place in the diagnosis of autism. Autism affects an estimated 1 in 100 births according to the Centers for Disease Control Prevention. Nearly 1.5 million Americans are
believed to be affected by autism.

Autism is a neurological disorder that affects the brain’s function and children with the condition have problems in social interaction and communication skills.

The researchers hope that early detection using the voice system can help autistic children by bringing early treatment.