According to an experiment by researchers at the Massachusetts Institute of Technology, it is possible to search for vocal biomarkers of Covid-19 by analyzing the sounds made by asymptomatic people when they speak. Infection would indeed have the ability to affect the proper functioning of the muscles necessary for speech, even in asymptomatic people.

It is often easy to know when colleagues are suffering from a severe cold: their stuffy nose gives them a lower voice or even a nasal tone. Infections can affect the quality of our voices in a variety of ways, but is this the case with the new coronavirus? It is now known that the infection it causes can cause loss of taste (ageusia) and / or smell (anosmia), but researchers from the Lincoln laboratory of the Massachusetts Institute of Technology (MIT) wanted to know in a study of whether changes could be detected in the voice of these patients, even when these changes are too subtle to be heard or noticed by those around them.

By processing the voice recordings of people infected with COVID-19 but not yet showing symptoms, these researchers found evidence of vocal biomarkers, or measurable indicators, of the disease. These biomarkers come from disturbances caused by infection in the muscles of the respiratory, laryngeal and articulatory systems. Although this research is still in its infancy, the first results establish a framework for studying these vocal changes in more detail. This discovery may also prove to be promising for the use of mobile applications in order to screen affected people, in particular asymptomatic ones.

Inflammation of the respiratory system changes the voice

“When symptoms appear, a person usually has difficulty breathing. Inflammation of the respiratory system affects the intensity with which air is exhaled when speaking. "Explain the researchers. "This air interacts with other potentially inflamed muscles on its journey to speech production. These interactions have an impact on the volume, pitch, stability and resonance of the voice. ” To conduct their study, the scientists searched YouTube to find videos of five celebrities or TV hosts who gave interviews when they were COVID-19 positive but asymptomatic.

They then searched for and downloaded interviews with these people before the COVID-19 epidemic arrived, with the best possible audio conditions, and then used algorithms to extract characteristics of the speech signals from each audio sample. "These vocal characteristics serve as proxies for the underlying movements of speech production systems. “, Says Professor Tanya Talkar, who participated in the study. By comparing the variety of sounds produced in the two types of audio extracts (with or without infection), they then noticed a lower complexity of the voice quality in the COVID-19 interviews compared to previous interviews.

A new type of screening with multiple possibilities

"These preliminary results suggest that biomarkers derived from the coordination of the vocal system may indicate the presence of COVID-19. “Note the researchers for whom the next step will be to work on real audio samples of people tested positive for COVID-19. Beyond collecting additional data to feed this research, the team plans to use mobile applications to implement it. In particular, they want to integrate voice screening for COVID-19 into the VoiceUp application, initially developed by the McGovern Institute for Brain Research to study the link between voice and depression.

“A detection system built into an application could detect infections early, before people get sick or for people who have no symptoms. "Says Professor Jeffrey Palmer, who led the research group. “Even after a diagnosis, this detection capability could help doctors remotely monitor their patients' progress or monitor the effects of a vaccine or drug treatment. The main difficulty to overcome is figuring out how to deal with confounding factors, those causing vocal changes such as the recording environment, the patient's emotional state or other illnesses.