Speech Recognition as a Transcription Aid: A Randomized Comparison With Standard Transcription
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
OBJECTIVE: Speech recognition promises to reduce information entry costs for clinical information systems. It is most likely to be accepted across an organization if physicians can dictate without concerning themselves with real-time recognition and editing; assistants can then edit and process the computer-generated document. Our objective was to evaluate the use of speech-recognition technology in a randomized controlled trial using our institutional infrastructure. DESIGN: Clinical note dictation from physicians in two specialty divisions was randomized to either a standard transcription process or a speech-recognition process. Secretaries and transcriptionists also were assigned randomly to each of these processes. MEASUREMENTS: The duration of each dictation was measured. The amount of time spent processing a dictation to yield a finished document also was measured. Secretarial and transcriptionist productivity, defined as hours of secretary work per minute of dictation processed, was determined for speech recognition and standard transcription. RESULTS: Secretaries in the endocrinology division were 87.3% (confidence interval, 83.3%, 92.3%) as productive with the speech-recognition technology as implemented in this study as they were using standard transcription. Psychiatry transcriptionists and secretaries were similarly less productive. Author, secretary, and type of clinical note were significant (p < 0.05) predictors of productivity. CONCLUSION: When implemented in an organization with an existing document-processing infrastructure (which included training and interfaces of the speech-recognition editor with the existing document entry application), speech recognition did not improve the productivity of secretaries or transcriptionists.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.016 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.002 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it