Event Date and Time:
Wednesday, June 4
12:00 pm – 1:00 pm Mountain Standard Time
- Event Format: Virtual via Zoom
- Tech Support Contact: con.ed@rm.edu
Description
Join us for a free webinar! We invite you to a special webinar led by Dr. Hasegawa-Johnson. The Speech Accessibility Project is working to improve automatic speech recognition (ASR) for people with atypical speech by building a large, diverse dataset. We ensure participant privacy, fair compensation, and collaboration through trusted community partners. So far, we’ve collected over 1,000 hours of speech from 1,500+ individuals with speech differences related to Parkinson’s, ALS, cerebral palsy, Down syndrome, or stroke. Portions of the data are now available to researchers advancing accessibility, with recruitment ongoing.
Objectives
Upon successful completion of this webinar, the student will be able to:
- The relationship between the quantity of speech training data and the utility of an automatic speech recognizer
- Meanings of a subset of the differential diagnostic patterns of dysarthria
- How people with stroke, Parkinson’s disease, ALS, cerebral palsy or Down syndrome may contribute their speech to the Speech Accessibility Project.
Primary Audience
Healthcare professionals, academic, or simply interested in speech technology
Faculty
Dr. Mark Hasegawa-Johnson
Mark A. Hasegawa-Johnson is the M.E. Van Valkenburg Professor of Electrical and Computer Engineering at the University of Illinois at Urbana-Champaign. His research converts facts about speech production into low-resource transfer learning algorithms that can be used to make speech technology more fair, more inclusive, and more accessible. Dr. Hasegawa-Johnson is a Fellow of the IEEE, of the Acoustical Society of America, and of the International Speech Communication Association, and he is currently Editor in Chief of the IEEE Transactions on Audio, Speech, and Language Processing.