Publication Details
BUT System Description to VoxCeleb Speaker Recognition Challenge 2019
Wang Shuai (DCGM FIT BUT)
Silnova Anna, MSc., Ph.D. (DCGM FIT BUT)
Matějka Pavel, Ing., Ph.D. (DCGM FIT BUT)
Plchot Oldřich, Ing., Ph.D. (DCGM FIT BUT)
VoxCeleb Speaker Recognition Challenge, Deep Neural Networks, ResNet, x-vector, PLDA, Cosine distance
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.
@INPROCEEDINGS{FITPUB12224, author = "Hossein Zeinali and Shuai Wang and Anna Silnova and Pavel Mat\v{e}jka and Old\v{r}ich Plchot", title = "BUT System Description to VoxCeleb Speaker Recognition Challenge 2019", pages = "1--4", booktitle = "Proceedings of The VoxCeleb Challange Workshop 2019", year = 2019, location = "Graz, AT", language = "english", url = "https://www.fit.vut.cz/research/publication/12224" }