# Diarisation using location tracking with agglomerative clustering

arXiv: https://arxiv.org/abs/2109.10598 · HTML: https://mlsanity.com/paper/2109.10598/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 39 references that are in the map.
- First posted on arXiv 22 Sep 2021.

## Builds on (most cited first, 10 of 10)

- [Auto-Tuning Spectral Clustering for Speaker Diarization Using Normalized Maximum Eigengap](https://mlsanity.com/paper/2003.02405/) (2020)
- [Advances in Online Audio-Visual Meeting Transcription](https://mlsanity.com/paper/1912.04979/) (2019)
- [Encoder-Decoder Based Attractors for End-to-End Neural Diarization](https://mlsanity.com/paper/2106.10654/) (2021)
- [The LOCATA Challenge: Acoustic Source Localization and Tracking](https://mlsanity.com/paper/1909.01008/) (2019)
- [Towards Neural Diarization for Unlimited Numbers of Speakers Using Global and Local Attractors](https://mlsanity.com/paper/2107.01545/) (2021)
- [The continuous categorical: a novel simplex-valued exponential family](https://mlsanity.com/paper/2002.08563/) (2020)
- [BUT System for the Second DIHARD Speech Diarization Challenge](https://mlsanity.com/paper/2002.11356/) (2020)
- [ResNeXt and Res2Net Structures for Speaker Verification](https://mlsanity.com/paper/2007.02480/) (2020)
- [Localization and Tracking of an Acoustic Source using a Diagonal Unloading Beamforming and a Kalman Filter](https://mlsanity.com/paper/1812.01521/) (2018)
- [Recursive Bayesian Filtering in Circular State Spaces](https://mlsanity.com/paper/1501.05151/) (2015)

## Abstract (arXiv)

Previous works have shown that spatial location information can be complementary to speaker embeddings for a speaker diarisation task. However, the models used often assume that speakers are fairly stationary throughout a meeting. This paper proposes to relax this assumption, by explicitly modelling the movements of speakers within an Agglomerative Hierarchical Clustering (AHC) diarisation framework. Kalman filters, which track the locations of speakers, are used to compute log-likelihood ratios that contribute to the cluster affinity computations for the AHC merging and stopping decisions. Experiments show that the proposed approach is able to yield improvements on a Microsoft rich meeting transcription task, compared to methods that do not use location information or that make stationarity assumptions.