Fact · Dictation
50percent
In an in-lab study, participants missed identifying over 50 percent of speech recognition errors when listening to audio output of the recognized text.
Checked against its source on October 16, 2026
In the source's own words
“participants missed identifying over 50% of speech recognition errors when listening to audio output of the recognized text”
Identifying speech input errors through audio-only interaction, Jonggi Hong and Leah Findlater, CHI 2018 Extended Abstracts (ACM), 2018, Abstract.
Open the original- What it measures
- Study 1 of four. The other three studies used an online crowdsourcing platform.
- What it does not show
- Audio review only. Visual proofreading of text was not measured.
Source
Cited on
- Dictation and Voice Typing: How to Talk Instead of TypeTopic
- Voice Access in Windows 11: Setup and How It WorksGuide
- Speech to Text for AI: Why Spoken Prompts Work BetterGuide
- Dictation Mistakes and How to Make Voice Typing AccurateGuide
- Dictation for Blind and Visually Impaired PeopleGuide
- Dictation for Academics, Researchers and ThesesGuide
- Does Dictation Change How You Write?Guide
- Do AI chatbots understand prompts with dictation errors?Question
- How do researchers dictate field notes?Question
- How do you proofread dictated text?Question
- How do you test dictation software before buying?Question
- Is dictated writing worse than typed writing?Question
- Is Windows Voice Access any good?Question
- What is the difference between speech to text and text to speech?Question
- Why does dictated text sound different from typed text?Question