Williamson earns NSF grant to improve speech-based applications
Donald Williamson, an assistant professor at the School of Informatics, Computing, and Engineering, has been awarded a grant for nearly $175,000 from the National Science Foundation to study human auditory perception in everyday noisy environments. This work will impact several speech-based applications, including prosthetics, robotics, and multimedia communication.
Williamson’s proposal aims to develop computational evaluation algorithms to better assess speech quality and intelligibility in real-world situations. That can improve the use of aids for the hearing impaired, who often struggle with listening fatigue, or the challenge that comes with separating speech from other amplified sounds when a user is in a crowded room.
“This grant means a lot to me personally,” Williamson said. “This is the first external grant that I have received, so I’m excited that peers in my field see the potential impact of my work. It reiterates that the problems that I am addressing are important problems that have several broader impacts.”
The grant will allow Williamson to begin data collection, field testing, and algorithm development. Since the focus of the project has not been heavily researched in the past, Williamson believes he has the potential to take great strides in how people process sound in various noisy environments.
“We have some understanding of this, but not enough,” Williamson said. “Understanding human perception better will lead to improved human-computer interaction through devices such as hearing aids and home assistants to name a few.”
Williamson earned his Ph.D. in computer science and engineering from The Ohio State University in 2016 and joined the faculty at IU that same year.
“This project has important real-world applications for the quality of life of people with hearing loss,” said Kay Connelly, associate dean for research at SICE. “Williamson’s work is yet another excellent example of how SICE research uses technical approaches to solving real world problems.”
For more information on machine learning at SICE, visit our website.
Phone: (812) 856-6908