Labeling who spoke when in a multi-speaker audio recording.
Reviewed:
Full definition
Diarization complements speech-to-text for meeting notes. Errors rise with overlapping speech and similar voices; human correction remains useful.
Related encyclopedia topic
Speech to Text
— Speech-to-text (STT), or automatic speech recognition (ASR), converts spoken audio into written text. It powers captions, meeting notes, voice interfaces, and…
