Publication Details
BUT System for CHiME-6 Challenge
Kocour Martin, Ing. (DCGM)
Landini Federico Nicolás (DCGM)
Beneš Karel, Ing. (DCGM)
Karafiát Martin, Ing., Ph.D. (DCGM)
Vydana Hari Krishna
Lozano Díez Alicia, Ph.D.
Plchot Oldřich, Ing., Ph.D. (DCGM)
Baskar Murali Karthick, Ing., Ph.D.
Švec Ján, Ing. (DCGM)
Mošner Ladislav, Ing. (DCGM)
Malenovský Vladimír, Ing., Ph.D. (DCGM)
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Yusuf Bolaji (DCGM)
Novotný Ondřej, Ing., Ph.D.
Grézl František, Ing., Ph.D. (DCGM)
Szőke Igor, Ing., Ph.D. (DCGM)
Černocký Jan, prof. Dr. Ing. (DCGM)
diarization, neural network, acoustic model, language model, enhancement
This paper describes BUTs efforts in the development of the system for the CHiME-6 challenge with far-field dinner party recordings [1]. Our experiments are on both diarization and speech recognition parts of the system. For diarization, we employ the VBx framework which uses Bayesian hidden Markov model with eigenvoice priors on x-vectors. For acoustic modeling, we explore using different subsets of data for training, different neural network architectures, discriminative training, more robust i-vectors, and semi-supervised training on Vox- Celeb data. Besides, we perform experiments with a neural network-based language model, exploring how to overcome the small size of the text corpus and incorporate across-segment context. When fusing our best systems, we achieve 41.21 % / 42.55 % WER on Track 1, for development and evaluation respectively, and 55.15% / 69.04 % on Track 2, for development and evaluation respectively.
@inproceedings{BUT164067,
author="Kateřina {Žmolíková} and Martin {Kocour} and Federico Nicolás {Landini} and Karel {Beneš} and Martin {Karafiát} and Hari Krishna {Vydana} and Alicia {Lozano Díez} and Oldřich {Plchot} and Murali Karthick {Baskar} and Ján {Švec} and Ladislav {Mošner} and Vladimír {Malenovský} and Lukáš {Burget} and Bolaji {Yusuf} and Ondřej {Novotný} and František {Grézl} and Igor {Szőke} and Jan {Černocký}",
title="BUT System for CHiME-6 Challenge",
booktitle="Proceedings of CHiME 2020 Virtual Workshop",
year="2020",
pages="1--3",
publisher="University of Sheffield",
address="Barcelona",
doi="10.21437/CHiME.2020-13",
url="https://www.isca-speech.org/archive/CHiME_2020/pdfs/CHiME_2020_paper_zmolikova.pdf"
}