French   Italian   Russian   English
 
German   Brazilian   Chinese   Spanish
News  
Development
Improving Speech Recognition with software
A professor at Tel-Aviv University has developed software that is believed to improve speech recognition by 50% for hearing aid and cochlear implant users. Prof. Miriam Furst-Yust from the School of Electrical Engineering said, “Hearing-impaired people have a real problem understanding speech. Their devices maybe useful in 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”. “Clearcall” is based on a cochlear model and can be added to existing devices. The software includes a mathematical model of the ear that shows how speech recognition works and it works by cleaning auditory information before it goes to the brain. “It takes some getting used to”, says Prof. Furst-Yust, “but people who have been wearing hearing aids all their lives have no problem getting the most from Clearcall.” 


CPI-EDP Santé - 25, rue Daviel - 75013 Paris - Group Publisher