Amazon, Google, Meta, Microsoft, and Apple may have competing interests, but they’ve recently found one thing to work together on: All five of these big tech companies have joined forces to support the Speech Accessibility Project at the University of Illinois at Urbana-Champaign (UIUC) to develop improved speech recognition software for people with certain disabilities that affect their speech patterns.
Individuals affected with conditions like amyotrophic lateral sclerosis (ALS, also known as Lou Gehrig’s disease), Down syndrome, Parkinson’s disease, or even just a minor speech impediment, have speech patterns that are a bit different from those without these conditions. Since speech recognition software is usually trained using data that comes from people without such disorders, automatic speech recognition software is not easily accessible for these individuals.
The Speech Accessibility Project hopes to change that, with a little help from the aforementioned tech companies and other organizations that advocate for people with these disabilities.
“The option to communicate and operate devices with speech is crucial for anyone interacting with technology or the digital economy today,” said Mark Hasegawa-Johnson, a UIUC professor of electrical and computer engineering who leads the Speech Accessibility Project. “Speech interfaces should be available to everybody, and that includes people with disabilities.”
The Speech Accessibility Project aims to collect a dataset of speech produced by people with disorders that affect their speech patterns, like ALS and Parkinson’s. Because these disabilities also impact an individual’s motor control, improved speech recognition could be particularly helpful for these populations, allowing them to communicate more effectively through digital means.
“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,” Hasegawa-Johnson said.