Tel Aviv, Israel - Software developers at Tel Aviv University have produced an application, Clearcall, that they say improves speech recognition for the hard-of-hearing by up to 50 percent.
Traditional hearing aids and cochlear implants amplify background sound as well as speech, so they're less effective in a noisy environment.
"Hearing-impaired people have a real problem understanding speech," says Professor Miriam Furst-Yust of the university's School of Electrical Engineering. "Their devices may be useful in a quiet room, but once the background noise levels ramp up, the devices become less useful. Our algorithm helps filter out irrelevant noise so they can better understand the voices of their friends and family."
Based on a cochlear model that she devised, the new patented technology is now being developed to improve the capabilities of existing cochlear implants and digital hearing aids. Adding Clearcall to current technology is quite straightforward, says Professor Furst-Yust, and requires only add-on software for existing devices. The software is available for licensing through Tel Aviv University's commercialization company, Ramot.
"We've developed a mathematical model of the ear that shows how speech recognition works. The math is complicated, but basically we're cleaning auditory information before it goes to the brain. We get rid of some of the information ― the background noise ― so that the hearing-impaired have an easier time 'filling in' missing information that their ears can't give them," explains Professor Furst-Yust.
To a person with normal hearing, a Clearcall-filtered voice will sound distorted, and even to the newly hearing impaired, Clearcall will sound different. But with continued use, the software improves the clarity of voices from 30 to 50 percent.
Professor Furst-Yust is currently preparing the results of her study for publication.