
Incoming pre-employment screening voodoo in 5..4..3..2..
The US National Institutes of Health (NIH) has earmarked as much as $14 million in funding to support the training of AI software that can analyze patients' voices to diagnose and study illness. Twelve research institutions led by the University of South Florida (USF) will receive the money to varying degrees over four years …
Momentary mood has an enormous impact on speech. I suspect it's far larger than the early markers of neurodegenerative disease. That brings me to the suspicion that somebody's looking for an excuse to illegally analyze a very large amount of recorded voice data.
Sure the science is good and you can make something work in a lab.
Zero chance of it operating well outside of those conditions tho, not with background noise, dodgy connections, people that hold their devices out in front of their face to talk.
You'd just end up with tons of false positives, or you'd have to tune the threshold so low you'd miss out genuine cases.
This post has been deleted by its author
This post has been deleted by its author