Glossary
Back-end speech recognition
Back-end speech recognition is a workflow in which the dictated audio is recognized and then edited by someone else, usually a transcriptionist, before it is signed. Its main trade-off is the cost and time of the second pass against the writer's own editing effort.
Updated October 17, 20264 cited facts, each traced to its source
Also called background speech recognition, deferred speech recognition.
Back-end speech recognition is a workflow in which the writer dictates, the recognizer produces a draft, and a different person edits the draft before it is final. The writer's job ends when they stop talking. Someone else listens to the audio, reads the draft and makes the corrections. The alternative is front-end speech recognition, where the writer edits their own text.
A transcriptionist edits the draft
Weiss describes back-end transcription as a process in which a transcriptionist listens to an audio file while viewing the text and making corrections 1. The U.S. Bureau of Labor Statistics lists reviewing and editing drafts prepared by speech recognition software among the usual duties of medical transcriptionists 2. In other words, the second editor's job has moved from typing the report to checking the machine's draft.
The second check lowers the error rate
The error counts show why the second check matters. In a 2018 study of dictated clinical documents, 96.3 percent of speech recognition drafts contained at least one error, against 58.1 percent after a transcriptionist edited them 3. After the drafts were edited, the error rate fell to 0.3 percent in the notes physicians signed 4.
The same trade article notes what the workflow costs. Back-end transcription relieves radiologists of clerical work, but it reduces cost savings and can produce variable turnaround times 1.
A concrete example
A physician dictates a discharge summary into a recorder at the end of a shift. The recognized draft goes into a transcription queue. A transcriptionist checks names, doses and dates against the audio, corrects the draft and returns it. The physician signs it the next morning. The physician's work ended at the microphone, and the turnaround depends on the queue.
Why it matters for dictation and typing
Back-end work takes the editing away from the writer, which suits people who have little time to edit. The price is that the writer is no longer the final check. The record is only as good as the editor and the process around them, so a writer who sends work to a second person still needs to read the signed version before it is final.
Related terms
- Front-end speech recognition is the workflow where the writer edits.
- Transcriptionist is the person who usually does the back-end edit.
- Turnaround time measures how long the second pass takes.
Guides that cover it
Evidence
Every number on this page, with where it comes from. Open a fact to see the exact words in its source.
- 1.
- 2.
- 3.
- 4.
Related terms
- Dictation for Work: Doctors, Lawyers, Writers, StudentsThe topic this term belongs to
- CopytakerA copytaker was a typist in a newspaper office who took down stories that reporters dictated over the telephone. The Collins English Dictionary defines the role this way, and it predates the computer-based filing that replaced it.
- Dictation templateA dictation template is a block of text saved under a short spoken phrase, so one phrase inserts the whole block. Dragon calls these auto-texts, and Microsoft's Dragon Medical One guide documents the command that creates one from selected text.
- Electronic health record (EHR)An electronic health record (EHR) is a digital record of a patient's health information, built up over time from visits across care settings. The federal eCQI glossary also calls it an electronic medical record (EMR), and it is where dictated and typed notes end up.
- Front-end speech recognitionFront-end speech recognition is a workflow in which the person who dictates also reviews, corrects and signs the text, instead of passing the audio to someone else. The term is most common in radiology, where it is set against back-end transcription.
- Medical scribeA medical scribe is a person, or more recently an AI tool, that records what happens in a clinical visit and writes it into the chart so the clinician can focus on the patient. The clinician remains responsible for the note and must check and sign it.
- Pajama timePajama time is the record-keeping that clinicians finish after their clinic day ends, often at home in the evening. A 2017 study of primary care clinicians measured 86 minutes of EHR work per weekday after clinic hours.
- Registered Healthcare Documentation Specialist (RHDS)The Registered Healthcare Documentation Specialist (RHDS) is a voluntary credential from AHDI for people who create healthcare documentation. It is awarded after an exam of 120 questions, and it is a prerequisite for the CHDS.
- ScopistA scopist edits the transcripts of official proceedings that court reporters create. Scopists are typically paid by the page, starting from $1.00 to $1.50 per page, and the role is also called transcript editor.
- SOAP noteA SOAP note is a structured clinical note with four parts: Subjective, Objective, Assessment and Plan. The format was developed by Larry Weed, and a StatPearls reference article describes it as a widely used documentation method for clinicians.
- Transcription line rateA transcription line is a unit of 65 characters, and the line count is the number of such units in a document. The transcription line rate is the price paid for each line, so the unit controls how transcribed work is measured.
Pages that use this term
- Dictation for Work: Doctors, Lawyers, Writers, StudentsTopic
- What Is Dictation? Voice Typing and Talk to Text ExplainedGuide
- Medical Transcription: The Job, the Pay and AIGuide
- Are medical transcription jobs still available in India?Question
- Is medical transcription being replaced by AI?Question
- What does a medical transcription editor do?Question
- What is medical transcription?Question
- Front-end speech recognitionGlossary