The University of Illinois Urbana-Champaign is joining forces with giant tech leaders Amazon, Apple, Google, Meta, and Microsoft on a Speech Accessibility Project to progress voice recognition and ensure it is more functional for people living with speech disabilities.
The Speech Accessibility Project will gather a section of samples from people with a variety of speech patterns and develop artificial intelligence to provide interfaces to support different speech.
Volunteers for the project will develop a privatised de-identified dataset that will be used to instruct machine learning models to clearly comprehend the difficulties of speech.
Mark Hasegawa-Johnson, the UIUC professor of electrical and computer engineering leading the project, said: “The option to communicate and operate devices with speech is crucial for anyone interacting with technology or the digital economy today. Speech interfaces should be available to everybody, and that includes people with disabilities.
“This task has been difficult because it requires a lot of infrastructure, ideally the kind that can be supported by leading technology companies, so we’ve created a uniquely interdisciplinary team with expertise in linguistics, speech, AI, security, and privacy to help us meet this important challenge.”
The project will feature many industry professionals and professors in speech and hearing science, alongside staff members from the university to produce a safe repository for the de-identified samples of speech.
Community organisations such as Davis Phinney Foundation and Team Gleason have supported the project, and will help in recruitment and user testing. Alongside this, they will also aid in providing important feedback at many stages of testing.
To learn more about the project, click here.
