Speaker diarization
Working out who said what in a recording.
The fuller definition
Speaker diarization groups speech segments by who appears to be speaking, often using anonymous labels such as Speaker 1 and Speaker 2.
- Audio segments
Different turns
- Clustering
Group similar voices
- Labels
Speaker 1 and Speaker 2
A simplified relationship, not a screenshot or a complete design.
A concrete example
A meeting transcript separates two speakers' turns before someone confirms their identities.
The distinction that matters
Separating voices does not necessarily identify people by name or establish that every turn is assigned correctly.
Related terms
Speech to text (STT)
Software that turns speech into text. Check names, numbers, and words it may have misheard.
FoundationsMultimodal
Able to work with more than text, such as images, audio, or video.
Reliability & securityEvaluation (eval)
Testing an AI tool on a set of tasks to see how well it actually does.
Where it is taught
What actually happens when you ask AI a question?Source and further reading
Google · Machine Learning GlossaryThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.