Speech Accessibility Project

Coming Together to Expand Voice Recognition

The purpose of this project is to develop and maintain a shared, secure repository of de-identified speech data, built from open-source software, to support the creation of technologies that improve the quality of life for people with disabilities such as Parkinson’s disease, ALS, cerebral palsy, and Down syndrome. Our team, Consortium Nova Habilitas (NOVA H), will serve as a communication channel among individuals with disabilities, organizations that advocate and support them, and researchers or developers interested in serving those needs. The project has launched with industry support from Amazon, Apple, Google, Meta, and Microsoft.

Text Transcription Team

Upcoming Presentation

Publications

  • Mark Hasegawa-Johnson, Xiuwen Zheng, Heejin Kim, Clarion Mendes, Meg Dickinson, Erik Hege, Chris Zwilling, Marie Moore Channell, Laura Mattie, Heather Hodges, Lorraine Ramig, Mary Bellard, Mike Shebanek, Leda Sarı, Kaustubh Kalgaonkar, David Frerichs, Jeffrey P. Bigham, Leah Findlater, Colin Lea, Sarah Herrlinger, Peter Korn, Shadi Abou-Zahra, Rus Heywood, Katrin Tomanek, & Bob MacDonald, (2024). Community-Supported Shared Infrastructure in Support of Speech Accessibility. Journal of speech, language, and hearing research : JSLHR, 1–14. Advance online publication.  https://doi.org/10.1044/2024_JSLHR-24-00122

Advising

  • Emma Mueller, Abigail Keasler, Liz Gremer, Sophie Campa, Corrie Penrod, Increasing the Speech Intelligibility of Individuals with Down Syndrome in AI Voice Assistants, Research Mentor(s): Heejin Kim, Linguistics & Alex Barkhimer, Speech & Hearing Science),  Undergraduate Research Symposium (URS), UIUC, 2024.
  • Corrie Penrode, Comparison of acoustic features of lexical stress in dysarthric speech, , Illinois Speech-Language-Hearing Association 65th Annual Convention, Rosemont, IL, February 6-7, 2025.

Collaborators

News