Fact · Transcription
The second DIHARD challenge used DER as its primary metric, without a collar and without excluding overlapping speech.
Checked against its source on October 17, 2026
In the source's own words
“DER is adopted as the primary evaluation metric, but without use of collars or exclusion of overlapping speech.”
The Second DIHARD Diarization Challenge: Dataset, task, and baselines, Neville Ryant et al., arXiv (Interspeech 2019 challenge paper), 2019, Section 1, Introduction (performance metrics).
Open the original- What it measures
- A collar is a short window around each speaker boundary that is not scored. Dropping it makes boundary mistakes count.
- What it does not show
- Scoring rules only compare across papers when they match. A DER from one scoring rule is not directly comparable with another.