Gender affects speech recognition accuracy rates

Article

A small study found a significantly higher rate of transcription errors in women compared with men using a commercial voice recognition application. Causes of the discrepancy may include the differences in the volume and frequency of speech between sexes or more fundamental differences in how the application was tested at time of development.

A small study found a significantly higher rate of transcription errors in women compared with men using a commercial voice recognition application. Causes of the discrepancy may include the differences in the volume and frequency of speech between sexes or more fundamental differences in how the application was tested at time of development.

Dr. Syed Mahmood Ali, a radiology resident at the University of Maryland Medical Center, and colleagues trained five male and five female radiology residents on a speech recognition system. They asked each resident to dictate a standardized set of 10 radiology reports containing a total of 2123 words. The generated reports were compared with the original reports, and error rates were calculated. Researchers defined the error rate as the sum of the number of word insertions and deletions divided by the total word count for a given report.

Error rates in the male population ranged from 0.025 to 0.139, with a mean of 0.082. Error rates in the female population ranged from 0.015 to 0.206, with a mean of 0.100.

"These error rates may have significant negative impact on reporting accuracy and output, disproportionately affecting female radiologists," Ali reported at the American Roentgen Ray Society meeting.

Newsletter

Stay at the forefront of radiology with the Diagnostic Imaging newsletter, delivering the latest news, clinical insights, and imaging advancements for today’s radiologists.

Recent Videos
New Research Examines Radiation Risks with CT Exposure Prior to Pregnancy
Diagnostic Imaging’s Weekly Scan: August 31 — September 6
New Echocardiography Research Suggests Emerging Marker for Cardiomyopathy Detection in Patients with Duchenne Muscular Dystrophy
© 2025 MJH Life Sciences

All rights reserved.