Technology
Speaker diarization
Separating who said what in a multi-speaker recording.
Speaker diarization is the ASR-adjacent capability of separating speakers in a recording — distinguishing the clinician from the patient (and from family members or interpreters).
For a clinical scribe this matters because the source of a statement changes its meaning: "I have chest pain" vs. "she says she has chest pain" are different clinical facts, and a scribe that can't tell who said what is much more prone to misattribution. Good diarization is a quiet but decisive feature.
Related tools
See also
- ASR (Automatic Speech Recognition) — The speech-to-text foundation under every ambient scribe.
- AI hallucination — When an AI model writes something confidently into a note that was never said.