Other
Speech recognition: Evaluation, implementation, and use
David L. Weiss, Applied Radiology, 2008
Read the originalRead on October 17, 2026
- What it is
- A trade article by David L. Weiss, MD, a clinical section head for imaging informatics, published December 14, 2008. It compares the two ways radiologists use speech recognition: editing their own reports, or sending dictated reports to back-end transcription, and it describes a hybrid model.
- How much weight it carries
- A peer-reviewed-style trade journal for radiologists, written by a practising imaging informatics leader. It is practical advice, not a controlled study, and it dates from 2008, before the current generation of recognition engines. Use it for how the two workflows are described, not for accuracy figures.
Facts taken from this source
- Weiss describes back-end transcription as a process in which a transcriptionist listens to an audio file while viewing the text and makes corrections.
“In this process a transcriptionist listens to an audio file while viewing the text and making corrections.” (Report editing section)
- Weiss describes one way to use speech recognition as having radiologists dictate, edit, correct and sign their own reports.
“One way to use speech recognition is to have radiologists dictate, edit, correct, and sign their own reports.” (Report editing section)