Jan van Santen, Ph.D., professor and head of the Center for Spoken Language Understanding (CLSU) at the OGI School of Science & Engineering, has received a three-year $300,000 grant from the National Science Foundation to build a model of human hearing within a "talking" computer so computer speech will sound more natural. Van Santen, a mathematical psychologist, was a longtime Bell Labs researcher who joined the Hillsboro, Ore.-based OHSU school to focus on ways to make speech technology useful for education and health.
Computer systems, obviously, do not hear the way humans do, though they can be trained to "talk," albeit without much intonation or expression. By creating a computer system that can better "listen" to what is being said, van Santen hopes the computer's speech ultimately will more closely resemble natural speech.
Van Santen and CSLU senior research associate Lois Black have received a one-year $30,000 grant from the Medical Research Foundation to study how reading styles affect students' story comprehension and test performance. He, along with Audiology Inc., based in Arden Hills, Minn., also received a $12,500 grant from the National Institutes of Health to develop a computer system that automates hearing tests.
"There is huge potential for speech technology that is useful for education and health," said van Santen. "We are trying to tap into the market and make our work helpful for the average person who has a learning or medical problem." Speech technology could someday be used to help illiterate people learn to read, to help non-native speakers learn English, and to give autistic people more ways to communicate, van Santen said.