Peer-reviewed research
Comparative Evaluation of Three Continuous Speech Recognition Software Packages in the Generation of Medical Reports
Eric G Devine et al., Journal of the American Medical Informatics Association, 2000
Read the originalRead on October 16, 2026
- What it is
- A peer-reviewed study in which twelve physicians dictated medical reports with three continuous speech recognition packages: IBM ViaVoice 98, Dragon NaturallySpeaking Medical Suite 3.0 and L&H Voice Xpress. The error rates were scored by a standard method.
- How much weight it carries
- Peer-reviewed and carefully scored, but it tests software from 1998 and 1999 with minimal training. The authors expect later generations to be more accurate, so use it for Dragon's history, not for today's accuracy.
Facts taken from this source
- In a 2000 peer-reviewed study of physicians dictating medical reports, Dragon NaturallySpeaking Medical Suite 3.0 had a vocabulary recognition error rate of 14.1 to 15.2 percent.
“Dragon software (14.1 to 15.2 percent)” (Results, abstract)
- In the 2000 study, IBM ViaVoice 98 had the lowest mean vocabulary error rate, 7.0 to 9.1 percent.
“The IBM software was found to have the lowest mean error rate for vocabulary recognition (7.0 to 9.1 percent)” (Results, abstract)
- In the 2000 study, the L&H Voice Xpress software had a mean vocabulary error rate of 13.4 to 15.1 percent.
“followed by the L&H software (13.4 to 15.1 percent)” (Results, abstract)
Pages that rest on this source
- Dictation for Work: Doctors, Lawyers, Writers, StudentsTopic
- Medical Dictation: Software, Devices and How It WorksGuide
- Best Dictation Software for Windows: Free and PaidGuide
- Dragon NaturallySpeaking: What It Is and Where It StandsGuide
- How Accurate Is Speech Recognition? The Real NumbersGuide
- How accurate is voice recognition software?Question
- Is Dragon NaturallySpeaking good for dyslexia?Question
- Is Dragon NaturallySpeaking worth it?Question
- What is the difference between Dragon Medical One and Dragon NaturallySpeaking?Question
- Why does speech recognition get names and jargon wrong?Question
- Custom vocabularyGlossary