# Diarization Error Decomposition Under Pause Annotation Ambiguity

arXiv: https://arxiv.org/abs/2609.11007 · HTML: https://mlsanity.com/paper/2609.11007/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Sep 2026.

## Built on by (most cited first, 1 of 1)

- [Anuvani-Diarization: Zero Shot Speaker Diarization and Annotation Conventions Across 22 Languages](https://mlsanity.com/paper/2610.20327/) (2026)

## Abstract (arXiv)

Speaker diarization evaluation is sensitive to ambiguity in pause annotation, which can inflate diarization error rate (DER) or obscure genuine model errors. We show that morphological closing, which has been used for pause-tolerant diarization evaluation, discards segment-level distinctions. Instead, we propose an exact, overlap-aware decomposition of standard DER into a pause-attributable component, consisting of errors compatible with pause filling, and a residual core component that can serve as a proxy for intrinsic diarization errors. The decomposition leaves DER unchanged, while the pause-attributable and core components vary monotonically with the pause threshold and eventually saturate. Experiments spanning synthetic transformations, annotation mismatch, cross-domain evaluation, and tight-boundary diarization show that the decomposition reveals error sources not apparent from standard DER.