Fact · Accessibility and health
The authors note that automatic speech recognition accuracy depends on the speech itself, ambient noise and microphone quality, as well as on computing power.
Checked against its source on October 16, 2026
In the source's own words
“ASR accuracy for any application can be affected by other variables including auditory factors such as speech fidelity, ambient noise and microphone quality”
Deaf, Hard of Hearing, and Hearing Perspectives on using Automatic Speech Recognition in Conversation, Abraham Glasser et al., ASSETS 2017 (also arXiv 1909.01176), 2017, Section 4, ASR for Conversational Use.
Open the original- What it measures
- This is why the same app can caption one room well and another poorly: the sound reaching the microphone sets a limit on what the software can recognize.
- What it does not show
- Describes factors that affect accuracy in general. It does not give the size of each effect.
Source
Cited on
- How Speech Recognition Works, From Sound to TextGuide
- Speech to Text for Deaf and Hard of Hearing PeopleGuide
- On-Device vs Cloud Speech Recognition: The TradeoffsGuide
- Can an ESP32 or microcontroller do speech recognition?Question
- Can you use dictation in an open-plan office?Question
- Do speech to text glasses work for deaf people?Question
- How do dictation machines work?Question
- How do you transcribe low-quality or quiet audio?Question
- Why is iPhone dictation so bad?Question