Department of Computer Science and Engineering Professor DeLiang (Leon) Wang will lead a five-year $1.8 million research grant from the National Institute on Deafness and Other Communication Disorders (NIDCD), one of the institutes that compromises the National Institutes of Health (NIH), to develop an algorithm to improve speech reception in noise by hearing-impaired listeners.
"My lab has developed a completely new approach to speech segregation that treats segregation as a classification problem, which has the potential to overcome the longstanding challenge of improving speech understanding in noisy background for millions of listeners with hearing loss. This NIH grant will enable us to further develop this approach and systematically test on hearing impaired subjects," says Wang.
Wang, in collaboration with co-investigator Eric Healy, associate professor, Department of Speech and Hearing Science, together with graduate students Sarah Yoho and Yuxuan Wang, has recently provided the first demonstration of speech intelligibility improvements by hearing-impaired listeners. All listeners in their study demonstrated improvements in sentence recognition following algorithm processing. These improvements were often quite substantial, as many listeners who were unable to understand any speech showed near-perfect recognition after processing.
This NIH project has the potential to revolutionize our treatment of hearing loss.
Wang received his BS and MS degrees from Peking University in Beijing. He then went on to receive a PhD in computer science from the University of Southern California. His research interests include machine perception and neurodynamics. In 2008, he won the Helmholtz Award from the International Neural Network Society. He is an IEEE Fellow, and currently serves as the co-editor-in-chief of Neural Networks, a premier journal in the field.