Publication detail

BUT System Description to VoxCeleb Speaker Recognition Challenge 2019

ZEINALI, H. WANG, S. SILNOVA, A. MATĚJKA, P. PLCHOT, O.

Original Title

BUT System Description to VoxCeleb Speaker Recognition Challenge 2019

Type

article in a collection out of WoS and Scopus

Language

English

Original Abstract

In this report, we describe the submission of Brno University of Technology (BUT) team to the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2019. We also provide a brief analysis of different systems on VoxCeleb-1 test sets. Submitted systems for both Fixed and Open conditions are a fusion of 4 Convolutional Neural Network (CNN) topologies. The first and second networks have ResNet34 topology and use twodimensional CNNs. The last two networks are one-dimensional CNN and are based on the x-vector extraction topology. Some of the networks are fine-tuned using additive margin angular softmax. Kaldi FBanks and Kaldi PLPs were used as features. The difference between Fixed and Open systems lies in the used training data and fusion strategy. The best systems for Fixed and Open conditions achieved 1.42 % and 1.26 % ERR on the challenge evaluation set respectively.

Keywords

VoxCeleb Speaker Recognition Challenge, Deep Neural Networks, ResNet, x-vector, PLDA, Cosine distance

Authors

ZEINALI, H.; WANG, S.; SILNOVA, A.; MATĚJKA, P.; PLCHOT, O.

Released

14. 9. 2019

Location

Graz

Pages from

1

Pages to

4

Pages count

4

URL

BibTex

@inproceedings{BUT168476,
  author="Hossein {Zeinali} and Shuai {Wang} and Anna {Silnova} and Pavel {Matějka} and Oldřich {Plchot}",
  title="BUT System Description to VoxCeleb Speaker Recognition Challenge 2019",
  booktitle="Proceedings of The VoxCeleb Challange Workshop 2019",
  year="2019",
  pages="1--4",
  address="Graz",
  url="https://arxiv.org/abs/1910.12592"
}