Vocalis, a voice analysis company with offices in Israel and the United States, introduced its new invention. The company previously built a smartphone app that could detect chronic obstructive pulmonary disease by listening for signs that users are short of breath when speaking.
The company wants to do the same with COVID-19. People who already tested positive for coronavirus can join just by downloading the Vocalis research app to their personal electronics. Once a day, they open an app and speak into their phone, describe an image in a loud voice, and count from 50 to 70.
After that, Vocalis began processing these recordings along with the voices of people tested negative using a machine learning system, thereby trying to identify voice patterns when COVID-19 was present.
By mid-summer, the company had more than 1,500 voice samples and a test version of the COVID-19 digital refinement engine.
The tool the company is currently testing around the world is not intended to give an accurate diagnosis, but it helps doctors classify potential cases, identify those at risk, need testing, how cup or most medical care.
This is not the only company participating in the race to find human voice models with COVID-19. There are at least three other research groups doing the same study. Other groups analyzed the cough recordings of people with COVID-19 and developed analytical systems to detect when someone was wearing a mask.
It’s a sign of just how desperate this fledgling field of speech diagnostics is to make its mark. Over the past decade, scientists have used artificial intelligence (AI) and machine learning systems to identify potential voice markers of a variety of health conditions, including dementia, depression, autism spectrum disorders and even heart disease.
The technologies they have developed are capable of detecting small differences in the way people talk with certain diseases, and companies around the world are starting to commercialize them.
Many companies want to be able to develop this technology more widely, using specialized microphones in home products to help homeowners identify diseases.
Björn Schuller is an expert in speech and emotional recognition – a joint position between the University of Augsburg in Germany and Imperial College London. “In the future, your Siri and Alexa will say, ‘Oh, it looks like you have a cold,'” he said.
This content is also available in: Tiếng Việt