Fact · Accessibility and health
Google states that automatic speech recognition systems are most often trained on typical speech, so people with speech impairments or heavy accents do not get the same benefit.
Checked against its source on October 16, 2026
In the source's own words
“ASR systems are most often trained from 'typical' speech”
Project Euphonia's Personalized Speech Recognition for Non-Standard Speech, Google Research, Google Research blog, 2019, Introduction.
Open the original- What it measures
- Google's explanation at the start of its 2019 post on Project Euphonia.
- What it does not show
- A statement of cause from the company that builds these recognizers. It is consistent with the measured error rates, but it is not a measurement in itself.
Source
Cited on
- Dictation Languages: What Each App and Device SupportsGuide
- Speech Recognition and Accents: Accuracy and FixesGuide
- Speech Recognition for Stuttering and DysarthriaGuide
- Can dictation help non-native English speakers write work emails?Question
- Does speech recognition work if you stutter?Question
- Does speech to text help autistic people?Question
- Is speech recognition less accurate for some people?Question
- What is the best voice to text app for elderly people?Question
- Why does iPhone dictation spell my name wrong?Question
- Why doesn't voice recognition understand my accent?Question