AI can now detect a person's cold through voice change

People are finding new ways to use artificial intelligence and exploring emerging technology on a large scale. And now, some researchers have reported that they can detect a person's cold by the tone of their voice.

While this could be useful in helping people spot the cold, it could also spell trouble for those employees who often "call in sick" under the guise of having a (false) "cold" when they are absolutely fine. If this technology becomes the next big thing in the future and leads to the development of another revolutionary product, employers could tell who has a cold and who doesn't by detecting the tone of their employees' voices during a call.

Researchers detect cold through voice change

According to a Business Insider report attributed initially to The Economist, researchers at the Sardar Vallabhbhai National Institute of Technology, Surat, successfully analyzed the vocal patterns of 630 people. 111 of these people suffered from a cold. Vocal patterns were analyzed to detect people who had a cold.

The report adds that the study used harmonics (vocal rhythms in human speech) to detect the cold in people. Harmonics decrease in amplitude when their frequency increases. And a person suffering from a cold may show an irregular cold pattern. Based on the same phenomenon, the researchers used machine learning algorithms to analyze the amplification differences of various individuals and identify those who had a cold.

The Economist also reported that test subjects were asked to count from 1 to 40 and then describe what they did over the weekend. They were asked to recite Aesop's fable, The North Wind and the Sun. The study's accuracy in detecting cold was 70 per cent.

According to them, the main intention was to identify if a person had a cold without needing a visit to the doctor.