A new “Speech Accessibility Project” led by The University of Illinois aims to expand voice recognition technology “more useful for people with a range of diverse speech patterns and disabilities.”
The project is launching with support from some of the industry giants, including Amazon, Apple, Google, Meta, and Microsoft.
Speech recognition isn’t fully accessible to people with speech disabilities, due to a lack of diverse and representative data. The lack of data makes it impossible for Machine Learning models behind speech recognition tech to learn and understand different types of speech. In essence, the Speech Accessibility Project aims to broaden the database available to “more effectively train these machine learning models.”
A new initiative at @BeckmanInst will make voice recognition technology more useful for people with a range of diverse speech patterns and disabilities.
— University of Illinois (@UofIllinois) October 3, 2022
“Millions of people will benefit from diverse and inclusive speech recognition. This may include but isn’t limited to people with Amyotrophic Lateral Sclerosis, Parkinson’s disease, cerebral palsy, Down syndrome and a wide range of medical and non-medical conditions that affect speech,” reads the project page.
Project volunteers will record speech samples from text prompts, which would be developed in collaboration with focus groups and disability community organizations. The recording would go in a “private, de-identified” dataset that would be used to train Machine Learning models. Notably, the tech giants mentioned above would use the data to train their specific speech recognition Machine Learning models. “Each of the companies supporting the Speech Accessibility Project is committed to leveraging project data to make improvements within their respective voice recognition products and services,” reads the project page.
Learn more about the project and how you can participate as a volunteer here.
Image credit: Shutterstock
Source: Speech Accessibility Project