Analysis of ABC Submission to NIST SRE 2019 CMN and VAST Challenge

Alam, Jahangir; Boulianne, Gilles; Burget, Lukas; Dahmane, Mohamed; Diez Sánchez, Mireia; Lozano-Diez, Alicia; Glembek, Ondrej; St-Charles, Pierre-Luc; Lalonde, Marc; Matejka, Pavel; Mizera, Petr; Monteiro, Joao; Mosner, Ladislav; Noiseux, Cedric; Novotný, Ondřej; Plchot, Oldrich; Rohdin, Johan; Silnova, Anna; Slavicek, Josef; Stafylakis, Themos; Wang, Shuai; Zeinali, Hossein

doi:10.21437/Odyssey.2020-41

Analysis of ABC Submission to NIST SRE 2019 CMN and VAST Challenge

Jahangir Alam, Gilles Boulianne, Lukas Burget, Mohamed Dahmane, Mireia Diez Sánchez, Alicia Lozano-Diez, Ondrej Glembek, Pierre-Luc St-Charles, Marc Lalonde, Pavel Matejka, Petr Mizera, Joao Monteiro, Ladislav Mosner, Cedric Noiseux, Ondřej Novotný, Oldrich Plchot, Johan Rohdin, Anna Silnova, Josef Slavicek, Themos Stafylakis, Shuai Wang, Hossein Zeinali

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.