In a study, it was revealed that the Covid-19 virus can be detected in the human voice using artificial intelligence.
Scientists from the Institute of Information Science at Maastricht University in the Netherlands have started a study on whether Covid-19 can be detected in human voices with a portable application using artificial intelligence.
In the study, 893 audio recordings (308 of which were positive for Covid-19) were analyzed from 4,353 healthy and unhealthy participants in Cambridge University’s Covid-19 Audio Application.
Experts used a scale called Mel-spectrogram, which shows the change in sound frequencies of the human ear, to analyze the recordings.
Wafaa Aljbawi, from the Institute of Data Science at Maastricht University, said, “We have developed different artificial intelligence models to distinguish the voices of those who do not have Covid-19 from other voices, and we evaluated which model gives better results in detecting Covid-19 events.” he said she.
Aljbawi noted that the Long Short Periodic Memory (LSTM) model gave better results than other artificial intelligence models.
In the research, it was noted that it provides 89 percent accuracy in detecting Covid-19 events with sound, and the accuracy of detecting people who do not have Covid-19 patients is 83 percent.
The results of the study were presented at the International Congress of the European Respiration Association held in Barcelona, Spain.
Researchers stated that this application is faster, easier and cheaper than antigen tests in the diagnosis of Covid-19.