Fact · Dictation for work and study
In a 2003 randomized comparison, Mohr and colleagues concluded that speech recognition did not improve the productivity of secretaries or transcriptionists in the organization they studied.
Checked against its source on October 16, 2026
In the source's own words
“speech recognition did not improve the productivity of secretaries or transcriptionists”
Speech Recognition as a Transcription Aid: A Randomized Comparison With Standard Transcription, David N Mohr et al., Journal of the American Medical Informatics Association, 2003, Abstract, Conclusion.
Open the original (DOI 10.1197/jamia.M1130)- What it measures
- Clinical note dictations from physicians in two specialty divisions were randomly assigned to standard transcription or to speech recognition, and so were the secretaries and transcriptionists who processed them. Productivity was hours of secretary work per minute of dictation processed.
- What it does not show
- One organization that already had a document-processing system, training, and a speech-recognition editor linked to its entry application, using an older recognizer. It measured transcription staff, not people drafting their own documents, so it does not settle the question for current software.