Signs of a coronavirus infection might be found in subtle changes in your voice, MIT research shows

Researchers found that changes in the movements of vocal muscles could be an indicator of whether someone has suffered an inflammation from Covid-19

Detection could eventually be used in apps to help identify asymptomatic carriers

Reading Time:2 minutes

A medical worker wearing a hazmat suit gets a swab sample at a health clinic in Wuhan to check if a man has the coronavirus on March 28. Photo: AFP

Published: 10:00pm, 10 Jul 2020Updated: 4:56am, 11 Jul 2020

Testing for Covid-19 currently involves a deep throat saliva sample or the dreaded nasal swab. But it might soon be as simple as listening to the sound of your voice.

By some estimates, asymptomatic carriers of the new coronavirus make up 40 per cent of all cases. Researchers at MIT believe changes in people’s voices might indicate whether or not they have been infected.

By analysing audio data from asymptomatic coronavirus carriers, researchers from the MIT Lincoln Laboratory have proposed a way to detect signs of Covid-19 by using audio samples. A person’s voice needs to be analysed by a computer, though, as the changes are too subtle to be picked up by human ears.

To conduct the test, the researchers used videos of five carriers from press conferences and interviews posted to YouTube, Instagram and Twitter. They analysed audio data from both before and after the carriers tested positive for the virus.

Major Preston Schaffner, of the 81st Civil Support Team, takes a swab sample from Scott Hennen, an asymptomatic volunteer, for a Covid-19 test in the car park of the FargoDome in Fargo, North Dakota on April 25. Photo: AFP

By using algorithms to analyse vocal signals, researchers detected disruptions in a person’s voice that could be caused by changes in movements of the larynx and muscles in the respiratory system. The researchers hypothesised that inflammation from the virus could cause less complex movement of the muscles across a person’s vocal systems as a result of becoming overly coupled.

Select Voice

Choose your listening speed

Get through articles 2x faster

1.25x

250 WPM

Slow

Average

Fast

00:0000:00

1.25x