Generate or retrieve a text alternative for audio/multimedia content
This feature includes transcription and gathering of text alternatives to multimedia content. This feature may be implemented in several ways:
- Automatic computerized transcription or captioning (voice-to-text) of audio, including live feeds, microphone input, and recorded media
- Retrieving existing transcripts or captions from other sources and linking them to the current media (e.g. a video of a presidential address may not be captioned, but is likely to have a transcript posted on a news website that can be presented to the user)
Discussion by Disabilities
Deaf and Hard of Hearing
Captions and transcripts allow people who are deaf or hard of hearing to understand the same media as their hearing peers, in real-time
Cognitive, Language, Learning Disabilities & Low Literacy
- Captions and transcripts may assist with language understanding for people with cognitive, language, and learning disabilities.
- Captions can also serve as a teaching tool for people with literacy problems who are learning to read a known language.
Related Research and Papers
- Inclusion of deaf students in computer science classes using real-time speech transcription – Villanova University – Kheir, R. and Way, T. (2007)
- Captioning for Deaf and Hard of Hearing People by Editing Automatic Speech Recognition in Real Time – University of Southampton – Wald, Mike (2006)