Researchers at Sardar Vallabhbhai National Institute of Technology in Surat have successfully used artificial intelligence to detect colds by analyzing changes in a person’s voice.
By analyzing the harmonics in a person’s speech, the researchers were able to identify people who were actually suffering from a cold. The study analyzed vocal patterns from 630 people, 111 of whom were suffering from a cold. The study’s accuracy in detecting colds was 70%.
While the primary intent of the study was to identify if a person is suffering from a cold without the need for a doctor’s visit, the Business Insider report also states that the study might interest employers who want to catch employees pretending to be sick in order to take time off work.
The test subjects were asked to count from 1 to 40, describe their weekend activities, and recite Aesop’s fable titled The North Wind and the Sun. The researchers utilized machine-learning algorithms to analyze the amplification differences of various individuals and identify those who had a cold.
This breakthrough could prove useful in helping people detect colds, but it could also mean trouble for those employees who often ‘call in sick’ on the pretext of suffering from a ‘cold’ when they are not actually sick. If this technology becomes the next big thing in the future and leads to the development of yet another revolutionary product, employers might be able to tell who has a cold and who does not by detecting the tone of their employees’ voices over a call.
