Fact · Typing and writing speed
The authors report that existing approaches for improving automatic speech recognition still fail to match trained CART captioners.
Checked against its source on October 16, 2026
In the source's own words
“these approaches still fail to perform at par with trained CART captioners”
CARTGPT: Improving CART Captioning using Large Language Models, Liang-Yuan Wu et al., ASSETS 2024, work-in-progress paper, 2024, Abstract.
Open the original- What it measures
- ASR is automatic speech recognition, the software that turns speech into text without a human transcriber.
- What it does not show
- The statement is from the authors' introduction and refers to approaches that try to improve ASR, not to every speech recognition product.
Source
Cited on
- Transcription: How to Turn Audio and Video Into TextTopic
- Human vs AI Transcription: Accuracy, Cost, SpeedGuide
- Speech to Text for Deaf and Hard of Hearing PeopleGuide
- Stenography and Shorthand: Writing at 225 WPMGuide
- Is automatic captioning accurate enough for deaf people?Question
- CART captioningGlossary