INTRODUCTION: Dictation of scientific articles has been recognised as an efficient method for producing high-quality, first article drafts. However, standardised transcription service by a secretary may not be available for all researchers and voice recognition software (VRS) may therefore be an alternative. The purpose of this study was to evaluate the out-of-the-box accuracy of VRS. METHODS: Eleven young researchers without dictation experience dictated the first draft of their own scientific article after thorough preparation according to a pre-defined schedule. The dictate transcribed by VRS was compared with the same dictate transcribed by an experienced research secretary, and the effect of adding words to the vocabulary of the VRS was investigated. The number of errors per hundred words was used as outcome. Furthermore, three experienced researchers assessed the subjective readability using a Likert scale (0-10). Dragon Nuance Premium version 12.5 was used as VRS. RESULTS: The median number of errors per hundred words was 18 (range: 8.5-24.3), which improved when 15,000 words were added to the vocabulary. Subjective readability assessment showed that the texts were understandable with a median score of five (range: 3-9), which was improved with the addition of 5,000 words. CONCLUSION: The out-of-the-box performance of VRS was acceptable and improved after additional words were added. Further studies are needed to investigate the effect of additional software accuracy training.
INTRODUCTION: Dictation of scientific articles has been recognised as an efficient method for producing high-quality, first article drafts. However, standardised transcription service by a secretary may not be available for all researchers and voice recognition software (VRS) may therefore be an alternative. The purpose of this study was to evaluate the out-of-the-box accuracy of VRS. METHODS: Eleven young researchers without dictation experience dictated the first draft of their own scientific article after thorough preparation according to a pre-defined schedule. The dictate transcribed by VRS was compared with the same dictate transcribed by an experienced research secretary, and the effect of adding words to the vocabulary of the VRS was investigated. The number of errors per hundred words was used as outcome. Furthermore, three experienced researchers assessed the subjective readability using a Likert scale (0-10). Dragon Nuance Premium version 12.5 was used as VRS. RESULTS: The median number of errors per hundred words was 18 (range: 8.5-24.3), which improved when 15,000 words were added to the vocabulary. Subjective readability assessment showed that the texts were understandable with a median score of five (range: 3-9), which was improved with the addition of 5,000 words. CONCLUSION: The out-of-the-box performance of VRS was acceptable and improved after additional words were added. Further studies are needed to investigate the effect of additional software accuracy training.