A group of researchers at Carnegie Mellon University and other institutions have published a site that they claim to be able to determine if you are getting coronavirus by simply analyzing your voice.
The site, which is alleged to perform coronavirus testing by voice, stands out as an interesting claim especially in the face of the shortage of test kits. “There is a lot of competition for the cheapest and fastest diagnosis you can do,” said Benjamin Striner, a graduate student working on the project from Carnegie Mellon University. Striner believes that the application can be a valuable tool to monitor the spread of the virus.
Using the Coronavirus Sound Detector, you can analyze your own voice for signs of infection, but the site has not been approved by the U.S. Food and Drug Administration and U.S. Centers for Disease Control and Prevention. Striner said that the site will never be as accurate as the test with the test kit in terms of diagnostics, on the other hand, it will easily follow millions of people.
Coronary virus detection by voice analysis:
Using the app is pretty simple if you have a smartphone or a computer with a microphone. Users are asked to cough several times, say a series of vowels and read the alphabet. The algorithm then gives you a score on whether you are caught in the coronavirus.
Rita Singh, a computer science professor at Carnegie Mellon University in the project; He created algorithms that describe micro-signatures in human voices that he believes reveal psychological, physiological and even medical data. Singh said, “The cough of coronavirus patients is very obvious. “It affects the lungs so badly that breathing and many other vital parameters are affected, and they have very strong signs with sound.”
It is difficult to measure the accuracy of the current version of the application, and both Striner and Singh reiterate that the results should not be considered medical advice. “The accuracy of the application cannot be tested right now because we don’t have the validated test samples we need,” said Singh. The researchers added that using people who have more healthy or any illnesses will benefit the algorithm. You can use the link here to try the site.