Speech Accessibility Project Aims To Make Voice Recognition Systems More Useful For People With Speech Impairment

a woman in a wheelchair is smiling. she is wearing a blue hoodie and gray sweatpants. a man to her right is seen embracing her and smiling with her.

University of Illinois at Urbana Champaign recently announced the Speech Accessibility Project in collaboration with some large tech companies like Amazon, Apple, Google, Meta, and Microsoft, as well as other not for profit organizations whose communities will benefit from this initiative.

Voice Assistants (Alexa, Siri, etc.) and other speech recognition systems today don’t do a good job of identifying voice commands from people who have diversity of speech patterns resulting from Lou Gehrig’s disease or Amyotropic Lateral Sclerosis, Parkinson’s disease, Cerebral Palsy, and Down syndrome. UIUC researchers will recruit paid volunteers to collect speech samples from individuals who have these speech patterns. There is heavy use of artificial intelligence and machine learning in speech recognition systems and these new speech samples will be used to train machine learning models more effectively and accommodate speech patterns representing people with speech impairment.

So why are all these companies joining hands? Because they all create solutions that use voice recognition so instead of duplicating efforts, they are all working together to create a common dataset that can be used by all. The belief that inclusive speech recognition should be a universal experience is the core fundamental driving this one of a kind collaboration.

Sign up for this research if you or someone you know is interested in participating in this multi year research project. Frequently asked questions are available if you want more information about this initiative.

Leave a comment

Your email address will not be published.


This site uses Akismet to reduce spam. Learn how your comment data is processed.