AI Transcription to Support Accessibility and Access for Digital Collections
Alternative Title
Artificial Intelligence (AI) Transcription to Support Accessibility and Access for Digital Collections
Contributor
University of Central Florida. Faculty Center for Teaching and Learning; University of Central Florida. Division of Digital Learning; Teaching and Learning with AI Conference (2024 : Orlando, Fla.)
Location
Sawgrass
Start Date
23-7-2024 1:30 PM
End Date
23-7-2024 2:00 PM
Publisher
University of Central Florida Libraries
Keywords:
Accessibility; Transcription; Digital collections; AI tools; Handwritten sources
Subjects
Archival materials--Digitization; Artificial intelligence--Library applications; Libraries--Special collections--People with disabilities; Computer-aided transcription systems; Technology--Archival resources
Description
The University of South Florida (USF's) Digital Collections is engaging human-in-the-loop AI tools to support the mass transcription of digitized handwritten primary sources. This session will provide an overview of USF's effort to achieve comprehensive, machine-readable, transcriptions for all records in the collection, with a specific emphasis on the significance of this work as a tool for improving collection accessibility for users with vision limitations or who simply struggle to read cursive. Included in this session will be an interactive demonstration with AWS Textract and READ-COOP's Transkribus.
Language
eng
Type
Presentation
Rights Statement
All Rights Reserved
Audience
Librarians, Faculty, General Audience
Recommended Citation
Boczar, Amanda, "AI Transcription to Support Accessibility and Access for Digital Collections" (2024). Teaching and Learning with AI Conference Presentations. 81.
https://stars.library.ucf.edu/teachwithai/2024/tuesday/81
AI Transcription to Support Accessibility and Access for Digital Collections
Sawgrass
The University of South Florida (USF's) Digital Collections is engaging human-in-the-loop AI tools to support the mass transcription of digitized handwritten primary sources. This session will provide an overview of USF's effort to achieve comprehensive, machine-readable, transcriptions for all records in the collection, with a specific emphasis on the significance of this work as a tool for improving collection accessibility for users with vision limitations or who simply struggle to read cursive. Included in this session will be an interactive demonstration with AWS Textract and READ-COOP's Transkribus.