Innovation is the key to success!
That’s what we have been reading since.. Well, since we understood the meaning of the word ‘innovation’. This phrase turns out to be of utter importance during the pandemic.
While the governments are trying to do their best by keeping people inside their houses the scientists are trying to use science to lessen the burden of testing. It is believed that the first step to fight the pandemic is large scale testing and that’s exactly what we lack. Testing kits.
So here’s what a team of researchers at Carnegie Mellon University and other institutions did. They have released an early version of an app called COVID Voice Detector that can determine if you have COVID-19, just by analyzing your voice.
While more and more people are trying to develop cheap and accurate means of detecting early Covid symptoms, the makers of the app believe there’s nothing cheaper and easier than someone speaking into their phones.
Currently, most of these efforts are at a stage in which the researchers are gathering data through speech and coughing recordings paired with information whether someone has an infection. These are then fed to AI algorithms, specifically deep learning and machine learning programmes.
So here’s how it works.
After logging in to the app, you will be asked to cough three times, recite an alphabet and say a vowel out loud for as long as you can, which helps the app in measuring a person’s lung capacity. The process takes less than five minutes and by the end of your test, you will receive a score between 1 to 10.
The score would tell whether your voice has the signs of COVID-19 or not. Before taking up the test, a person is required to provide their height and weight details and whether they have symptoms of COVID-19 or not.
However, the researchers have made it very clear that the app is certainly not a diagnostic system and hence it should not be used as a substitute to tests conducted at a medical laboratory. The app is aimed as a preliminary after which people consult a doctor.
Rita Singh, a professor of computer science at Carnegie Mellon in her interview stated that, since the voice production mechanism is so complex and dependent on cognitive abilities, any factor that affects your body or your mind will reflect in your voice.
The changes can be in fractions of seconds, what we call “micro” signatures, that are not audible to the untrained listener, but nevertheless present.
She also said that any condition affecting the lungs or the respiratory system has been established in the cases of Covid-19 infections that have a palpable effect on voice. Moreover, the cough of a Covid patient is also distinct from a healthy person’s.
To gather that data, the team reached out to colleagues around the world. Those colleagues didn’t just help them gather audio from COVID-19 patients, but also patients with other viruses, so that they could teach the algorithm to spot the differences.
They even pored over news videos to find interviews with patients, and add those to the dataset as well.