Analysis of BUT Submission in Far-Field Scenarios of VOiCES 2019 Challenge

Pavel Matějka, Oldřich Plchot, Hossein Zeinali, Ladislav Mošner, Anna Silnova, Lukáš Burget, Ondřej Novotný, Ondřej Glembek

This paper is a post-evaluation analysis of our efforts in VOiCES 2019 Speaker Recognition challenge. All systems in the fixed condition are based on x-vectors with different features and DNN topologies. The single best system reaches minDCF of 0.38 (5.25% EER) and a fusion of 3 systems yields minDCF of 0.34 (4.87% EER).We also analyze how speaker verification (SV) systems evolved in last few years and show results also on SITW 2016 Challenge. EER on the core-core condition of the SITW 2016 challenge dropped from 5.85% to 1.65% for system fusions submitted for SITW 2016 and VOiCES 2019, respectively. The less restrictive open condition allowed us to use external data for PLDA adaptation and achieve additional small performance improvement. In our submission to open condition, we used three x-vector systems and also one system based on i-vectors.

 DOI: 10.21437/Interspeech.2019-2471

Cite as: Matějka, P., Plchot, O., Zeinali, H., Mošner, L., Silnova, A., Burget, L., Novotný, O., Glembek, O. (2019) Analysis of BUT Submission in Far-Field Scenarios of VOiCES 2019 Challenge. Proc. Interspeech 2019, 2448-2452, DOI: 10.21437/Interspeech.2019-2471.

  author={Pavel Matějka and Oldřich Plchot and Hossein Zeinali and Ladislav Mošner and Anna Silnova and Lukáš Burget and Ondřej Novotný and Ondřej Glembek},
  title={{Analysis of BUT Submission in Far-Field Scenarios of VOiCES 2019 Challenge}},
  booktitle={Proc. Interspeech 2019},