Fact · Dictation software
0.080p value
In the pilot, the difference in mean word error rate across all errors was not statistically significant.
Checked against its source on October 16, 2026
In the source's own words
“The mean WER was 1.75% for Whisper and 1.54% for Dragon (p = 0.080).”
The use of generative artificial intelligence-based dictation in a neurosurgical practice: a pilot study, Benjamin S. Hopkins et al., Neurosurgical Focus, 2025, Results.
Open the original (DOI 10.3171/2025.4.FOCUS24834)- What it measures
- The p value is reported in the study's results, next to both mean error rates.
- What it does not show
- A small pilot has low power to detect small differences.
Source
Cited on
- Dictation Software: How to Choose the Right AppTopic
- Dictation for Work: Doctors, Lawyers, Writers, StudentsTopic
- Transcription: How to Turn Audio and Video Into TextTopic
- AI Dictation: How AI Voice Typing WorksGuide
- Medical Dictation: Software, Devices and How It WorksGuide
- What Is Dictation Software? Types and How It WorksGuide
- Dragon NaturallySpeaking Alternatives, Free and PaidGuide
- Is AI dictation better than Dragon NaturallySpeaking?Question
- Is AI dictation more accurate than built-in dictation?Question
- Is there a medical dictation app for iPhone and Android?Question
- What is the best medical dictation software for Mac?Question
- What is the best medical dictation software for Windows?Question
- What is the best medical dictation software?Question
- What is the best speech recognition software for Windows?Question
- What is the most accurate dictation software?Question
- Why does speech recognition get names and jargon wrong?Question