BUT Text-Dependent Speaker Verification System for SdSV Challenge 2020

Alicia Lozano-Diez, Anna Silnova, Bhargav Pulugundla, Johan Rohdin, Karel Veselý, Lukáš Burget, Oldřich Plchot, Ondřej Glembek, Ondvrej Novotný, Pavel Matějka

In this paper, we present the winning BUT submission for the text-dependent task of the SdSV challenge 2020. Given the large amount of training data available in this challenge, we explore successful techniques from text-independent systems in the text-dependent scenario. In particular, we trained x-vector extractors on both in-domain and out-of-domain datasets and combine them with i-vectors trained on concatenated MFCCs and bottleneck features, which have proven effective for the text-dependent scenario. Moreover, we proposed the use of phrase-dependent PLDA backend for scoring and its combination with a simple phrase recognizer, which brings up to 63% relative improvement on our development set with respect to using standard PLDA. Finally, we combine our different i-vector and x-vector based systems using a simple linear logistic regression score level fusion, which provides 28% relative improvement on the evaluation set with respect to our best single system.

 DOI: 10.21437/Interspeech.2020-2882

Cite as: Lozano-Diez, A., Silnova, A., Pulugundla, B., Rohdin, J., Veselý, K., Burget, L., Plchot, O., Glembek, O., Novotný, O., Matějka, P. (2020) BUT Text-Dependent Speaker Verification System for SdSV Challenge 2020. Proc. Interspeech 2020, 761-765, DOI: 10.21437/Interspeech.2020-2882.

  author={Alicia Lozano-Diez and Anna Silnova and Bhargav Pulugundla and Johan Rohdin and Karel Veselý and Lukáš Burget and Oldřich Plchot and Ondřej Glembek and Ondvrej Novotný and Pavel Matějka},
  title={{BUT Text-Dependent Speaker Verification System for SdSV Challenge 2020}},
  booktitle={Proc. Interspeech 2020},