Fact · Transcription
16milliseconds (model output resolution)
Bredin and Laurent's 2021 segmentation model works on 5-second audio chunks at a temporal resolution of every 16 milliseconds.
Checked against its source on October 17, 2026
In the source's own words
“our model operates on short audio chunks (5 seconds) but at a much higher temporal resolution (every 16ms)”
End-to-end speaker segmentation for overlap-aware resegmentation, Hervé Bredin and Antoine Laurent, Interspeech 2021, 2021, Abstract.
Open the original- What it measures
- The frame rate of a diarization model limits how precisely it can place a speaker change.
- What it does not show
- The resolution describes the model's output frames. Final timestamps in a transcript can be coarser.