We present a condensed description and analysis of the joint submission of ABC team for NIST SRE 2019, by BUT, CRIM, Phonexia, Omilia and UAM. We concentrate on challenges that arose during development and we analyze the results obtained on the evaluation data and on our development sets. The conversational telephone speech (CMN2) condition is challenging for current state-of-the-art systems, mainly due to the language mismatch between training and test data. We show that a combination of adversarial domain adaptation, backend adaptation and score normalization can mitigate this mismatch. On the VAST condition, we demonstrate the importance of deploying diarization when dealing with multi-speaker utterances and the drastic improvements that can be obtained by combining audio and visual modalities.
Cite as: Alam, J., Boulianne, G., Burget, L., Dahmane, M., Diez Sánchez, M., Lozano-Diez, A., Glembek, O., St-Charles, P.-L., Lalonde, M., Matejka, P., Mizera, P., Monteiro, J., Mosner, L., Noiseux, C., Novotný, O., Plchot, O., Rohdin, J., Silnova, A., Slavicek, J., Stafylakis, T., Wang, S., Zeinali, H. (2020) Analysis of ABC Submission to NIST SRE 2019 CMN and VAST Challenge. Proc. The Speaker and Language Recognition Workshop (Odyssey 2020), 289-295, doi: 10.21437/Odyssey.2020-41
@inproceedings{alam20_odyssey,
author={Jahangir Alam and Gilles Boulianne and Lukas Burget and Mohamed Dahmane and Mireia {Diez Sánchez} and Alicia Lozano-Diez and Ondrej Glembek and Pierre-Luc St-Charles and Marc Lalonde and Pavel Matejka and Petr Mizera and Joao Monteiro and Ladislav Mosner and Cedric Noiseux and Ondřej Novotný and Oldrich Plchot and Johan Rohdin and Anna Silnova and Josef Slavicek and Themos Stafylakis and Shuai Wang and Hossein Zeinali},
title={{Analysis of ABC Submission to NIST SRE 2019 CMN and VAST Challenge}},
year=2020,
booktitle={Proc. The Speaker and Language Recognition Workshop (Odyssey 2020)},
pages={289--295},
doi={10.21437/Odyssey.2020-41}
}