An app to diagnose COVID-19 needs nothing more than a voice sample, according to an Israel-based company. In tests of 2,000 participants, the app achieved an accuracy rate of 81.2%, including asymptomatic carriers …
TNW reports.
To ensure consistency in the data, and preserve privacy, users are simply asked to count upwards from 50 to 70 to provide the voice sample. The accuracy rate found in the trial is comparable to that of lateral flow rapid tests, but eliminates the need for test kits.
Vocalis collects a lot of data related to a person’s voice. It has developed a technology that identifies characteristics of a potential disease based on the analysis of voice collected from a person.
The firm’s algorithm extracts 512 features from a voice sample and makes an image — a spectrogram — with which it can diagnose possible diseases.
When the company aims to help detect a specific disease, it first holds clinical trials to recognize what kind of voice recordings it would need to collect to identify it, and what signatures in the audio it will need to pinpoint.
For instance, to detect COVID-19 the AI needs to identify characteristics of symptoms such as fever, headache, and shortness of breath […]
The company’s pre-training dataset includes over 275,000 different speakers in various languages to make it universally accessible.
The bad news is that it doesn’t sound like you or I will get access to the app: Vocalis seems focused on selling it to companies to screen their employees before a return to the office.
Some countries are experiencing a third wave of COVID-19 infections, with Apple Stores in France closing in response to a third national lockdown.
Vocalis’ tools are currently deployed in the US, Chile, Indonesia, South Africa, Romania, and Luxembourg in the public and private sectors […] It’s looking to commercialize the solution and make it available for more regions.
