This paper describes the winning systems developed by the BUT team for the four tracks of the Second DIHARD Speech Diarization Challenge. For tracks 1 and 2 the systems were mainly based on performing agglomerative hierarchical clustering (AHC) of x-vectors, followed by another x-vector clustering based on Bayes hidden Markov model and variational Bayes inference. We provide a comparison of the improvement given by each step and share the implementation of the core of the system. For tracks 3 and 4 with recordings from the Fifth CHiME Challenge, we explored different approaches for doing multi-channel diarization and our best performance was obtained when applying AHC on the fusion of per channel probabilistic linear discriminant analysis scores.
@article{arxiv.2002.11356,
title = {BUT System for the Second DIHARD Speech Diarization Challenge},
author = {Federico Landini and Shuai Wang and Mireia Diez and Lukáš Burget and Pavel Matějka and Kateřina Žmolíková and Ladislav Mošner and Anna Silnova and Oldřich Plchot and Ondřej Novotný and Hossein Zeinali and Johan Rohdin},
journal= {arXiv preprint arXiv:2002.11356},
year = {2020}
}