Publication Details
Analysis of the BUT Diarization System for Voxconverse Challenge
Glembek Ondřej, Ing., Ph.D.
Matějka Pavel, Ing., Ph.D. (DCGM)
Rohdin Johan Andréas, M.Sc., Ph.D. (DCGM)
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Diez Sánchez Mireia, M.Sc., Ph.D. (DCGM)
Silnova Anna, M.Sc., Ph.D. (DCGM)
Speaker Diarization, Variational Bayes, HMM, VoxConverse, VoxSRC Challenge
This paper describes the system developed by the BUT team for the fourth track of the VoxCeleb Speaker Recognition Challenge, focusing on diarization on the VoxConverse dataset. The system consists of signal pre-processing, voice activity detection, speaker embedding extraction, an initial agglomerative hierarchical clustering followed by diarization using a Bayesian hidden Markov model, a reclustering step based on per-speaker global embeddings and overlapped speech detection and handling. We provide comparisons for each of the steps and share the implementation of the most relevant modules of our system. Our system scored second in the challenge in terms of the primary metric (diarization error rate) and first according to the secondary metric (Jaccard error rate).
@inproceedings{BUT175790,
author="Federico Nicolás {Landini} and Ondřej {Glembek} and Pavel {Matějka} and Johan Andréas {Rohdin} and Lukáš {Burget} and Mireia {Diez Sánchez} and Anna {Silnova}",
title="Analysis of the BUT Diarization System for Voxconverse Challenge",
booktitle="ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",
year="2021",
pages="5819--5823",
publisher="IEEE Signal Processing Society",
address="Toronto, Ontario",
doi="10.1109/ICASSP39728.2021.9414315",
isbn="978-1-7281-7605-5",
url="https://ieeexplore.ieee.org/document/9414315"
}