Comparative analysis of automated speech recognition technologies for enhanced audiovisual accessibility
The accessibility of digital audiovisual (AV) collections is a difficult legal and ethical area that nearly all academic libraries will need to navigate at some point. The inclusion of AV accessibility features like captions and transcripts enormously benefit users with disabilities in addition to p...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Code4Lib
2023-12-01
|
| Series: | Code4Lib Journal |
| Online Access: | https://journal.code4lib.org/articles/17820 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The accessibility of digital audiovisual (AV) collections is a difficult legal and ethical area that nearly all academic libraries will need to navigate at some point. The inclusion of AV accessibility features like captions and transcripts enormously benefit users with disabilities in addition to providing extra value to the repository more universally. However, implementing these features has proven challenging for many reasons. Recent technological advancements in automatic speech recognition (ASR) and its underlying artificial intelligence (AI) technology offer an avenue for librarians in stewarding more accessible collections. This article will discuss these opportunities and present research from Florida State University Libraries evaluating the performance of different ASR tools. The authors will also present an overview of basic AV accessibility-related concepts, ethical issues in using AI technology, and a brief technical discussion of captioning formats. |
|---|---|
| ISSN: | 1940-5758 |