IISc researchers working on tool to detect coronavirus based on cough, speech sounds

A team of researchers at the Indian Institute of Science (IISc) is working on developing a tool to diagnose COVID-19, based on respiratory, cough and speech sounds. 

The Indian Institute of Science (IISc) Bangalore has announced that a team of researchers at the institute is working on developing a tool for diagnosis of coronavirus, which is based on respiratory, cough and speech sounds. If the tool gets the validation, then it can be made useful in minimizing the risk of exposure to the healthcare professional and for providing the results faster than the current testing method.

The eight-member team at IISc has named the project 'Coswara'.It has been developed with an aim to detect and quantify biomarkers of the disease in the acoustics of these sounds.

While commenting on the project, the team said, "As the pandemic is growing in numbers, the development of simplistic, cost-effective and fast testing for infection has become a crucial component in healthcare, policymaking and economic revival of several countries."

"The major symptoms of the disease are associated with respiratory problems. The proposed project aims to detect and quantify the biomarkers of the disease in the acoustics of these sounds. The project requires participants to perform a recording of breathing sounds, cough sounds, sustained phonation of vowel sounds and a counting exercise. The entire response requires about five minutes of recording time," a team member said.

"While doing these recordings, the tool will also record the patient's health status as well as age, gender, and location, without any personally identifiable information. The audio dataset collected will be released for researchers across the world to develop a potential diagnostic tool using signal processing and machine learning methods," he added.

The project is supervised by the IISc faculty, Sriram Ganapathy, and is currently in the data collection stage. The tool will go through the experimental validation before obtaining full approval as a potential diagnostic tool.

Read More: