FUTURISM.com Reports … You can use the COVID Voice Detector now to analyze your own voice for signs of infection, though it comes with a hefty disclaimer that it’s “not a diagnostic system,” not approved by the FDA or CDC, and shouldn’t be used as a substitute for a medical test or examination. The researchers behind the project emphasize that the app is a work in progress.
APRIL 1, 2020
“This is an AI-powered system that analyzes your voice and gives you a score …” ~Carnegie Mellon University
Carnegie Mellon University, voca.ai, telling.ai, hat-ai.com and Incremental Healthcare LLC collaboratively bring you this experimental system designed to detect signatures of Covid-19 infections in your voice. This is a free service.
We are a team of voice scientists and engineers who work on voice forensic technologies. The Covid-19 pandemic is spreading rapidly across the world. There is a growing shortage of medical testing facilities. Tens of thousands of potentially infected people who need to be tested do not have easy access to medical tests. Our goal is to develop a voice-based testing system for Covid-19, that could potentially reach every person in the world.
“If the app is to be put out as a public service, it, and our results, will have to be verified by medical professionals, and attested by an agency such as the CDC,” Raj added. “Until that happens, its still very much an experimental and untrustworthy system. I urge people not to make healthcare decisions based on the scores we give you. You could be endangering yourself and those around you.”
And at the end of the day, it’s unlikely the app will ever be as accurate as a laboratory test.
“In terms of diagnostics, of course, it’s never going to be as as accurate as taking a swab and putting it on some agar and waiting for it to grow,” said Striner, who has been working around the clock to prepare the app for release. “But in terms of very easily monitoring a ton of people daily, weekly, whatever, monitoring on a very large scale, it gives you a way to handle and track health outbreaks.”
This website provides Covid-19 assessment from voice. You may try it out, but please see the disclaimer below. To make this system accurate, we urgently need examples of voices from healthy and infected people. Please use this system to donate your voice. Please ask your friends family to also do so. Together we may help save lives.
What this system currently provides: This is an AI-powered system that analyzes your voice and gives you a score. The score is a rating on a scale of 1-10 that tells you the likelihood that your voice carries signatures of Covid-19. The higher the returned rating, the greater the likelihood that you may be infected. In addition, the system provides an assessment of your lung capacity where possible.
Please remember that this system is still very much under development. It will improve as we obtain more data from healthy and infected individuals. Everyone is urged to contribute data, particularly if you are or have been infected. Please act responsibly and provide accurate information. The accuracy of the data we obtain will dictate our ability to succeed.
- https://cvd.lti.cmu.edu/cvd/login; Carnegie Mellon University; 5000 Forbes Avenue; Pittsburgh, PA 15213; 412-268-2000
RELATED STORY | Read More Below |
AI-powered app analyzes the user’s voice to determine if they are infected with the coronavirus
A new app could determine if you may have contracted the coronavirus just by analyzing your voice.
Researchers at Carnegie Mellon University have developed an AI-powered system that analyzes your voice and provides a score on the likelihood it contains signatures of the virus.
The technology picks up breathing patterns and other vital parameters, as the coronavirus greatly affects the lungs.
The team is urging the public, healthy or infected, to share a recording of their voice in order to help improve the algorithm.
Scroll down for video
Researchers at Carnegie Mellon University have developed an AI-powered system that analyzes your voice and provides a score on the likelihood it contains signatures of the virus. Pictured is a woman who is delivering medications during the outbreak
The app, called COVID Voice Detector, is still in the early stages and comes with the disclaimer that it is not approved by the FDA or CDC, and ‘it shouldn’t be used as a substitute for a medical test or examination,’ Futurism reported.
The coronavirus (COVID-19) first made headlines in December 2019, when cases began popping up in Wuhan, China.
Within a few weeks it had spread throughout the country and has now infected nearly every part of the world.
As of Tuesday, there are more than 786,000 cases and over 37,000 deaths reported around the globe.
And with the cases continuing to rise, so has the shortage of test kits available, but that is why Carnegie Melon has developed their new app.
The coronavirus (COVID-19) first made headlines in December 2019, when cases began popping up in Wuhan, China. Within a few weeks it had spread throughout the country and has now infected nearly every part of the world
Benjamin Striner, a Carnegie Mellon graduate student who worked on the project, in an interview with Futurism: ‘I’ve seen a lot of competition for the cheapest, fastest diagnosis you can have.’
‘And there are some pretty good ones that are actually really cheap and pretty accurate, but nothing’s ever going to be as cheap and as easy as speaking into a phone.
Although the app is still in the development stage, Striner believes it could be vital to healthcare officials once it is released.
It uses a ranking from one to 10 when analyzing the person’s voice – the higher the ranking the more likely the individual has coronavirus.
To use the app, the person would cough several times when prompted and say a few different vowel sounds and recite the alphabet.
And the tool then presents a score in a download progress bar.
The team has gathered recordings from 19 individuals who have tested positive for the virus and those with other viruses in order to train the algorithm to spot coronavirus.
However, as the app says it should not be used as a sole means of diagnoses and Striner noted that they have yet to test the accuracy because they do not ‘have the verified test instance’ they need.
If it comes from a healthy person, we then have examples of what ‘healthy’ sounds like,’ he told Furturism,
‘If it comes from a person who has some known respiratory condition, we then know what that condition sounds like.
‘The system will use all that data as counterexamples, and for disambiguating COVID signatures from those of other confusing conditions.’