Publication Details

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

ALAM Jahangir, BOULIANNE Gilles, BURGET Lukáš, DAHMANE Mohamed, DIEZ Sánchez Mireia, GLEMBEK Ondřej, LALONDE Marc, LOZANO Díez Alicia, MATĚJKA Pavel, MIZERA Petr, MOŠNER Ladislav, NOISEUX Cédric, MONTEIRO Joao, NOVOTNÝ Ondřej, PLCHOT Oldřich, ROHDIN Johan A., SILNOVA Anna, SLAVÍČEK Josef, STAFYLAKIS Themos, ST-CHARLES Pierre-Luc, WANG Shuai and ZEINALI Hossein. Analysis of ABC Submission to NIST SRE 2019 CMN and VAST Challenge. In: Proceedings of Odyssey 2020 The Speaker and Language Recognition Workshop. Tokyo: International Speech Communication Association, 2020, pp. 289-295. ISSN 2312-2846. Available from: https://www.isca-speech.org/archive/Odyssey_2020/abstracts/73.html

Czech title

Analýza systému ABC pro evaluaci NIST SRE 2019 v kategoriích CMN a VAST

Type

conference paper

Language

english

Authors

Alam Jahangir (CRIM)
Boulianne Gilles (CRIM)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Dahmane Mohamed (CRIM)
Diez Sánchez Mireia, M.Sc., Ph.D. (DCGM FIT BUT)
Glembek Ondřej, Ing., Ph.D. (DCGM FIT BUT)
Lalonde Marc (CRIM)
Lozano Díez Alicia, Ph.D. (DCGM FIT BUT)
Matějka Pavel, Ing., Ph.D. (DCGM FIT BUT)
Mizera Petr (OMILIA)
Mošner Ladislav, Ing. (DCGM FIT BUT)
Noiseux Cédric (CRIM)
Monteiro Joao (CRIM)
Novotný Ondřej, Ing., Ph.D. (DCGM FIT BUT)
Plchot Oldřich, Ing., Ph.D. (DCGM FIT BUT)
Rohdin Johan A., Dr. (DCGM FIT BUT)
Silnova Anna, MSc., Ph.D. (DCGM FIT BUT)
Slavíček Josef (Phonexia)
Stafylakis Themos (OMILIA)
St-Charles Pierre-Luc (CRIM)
Wang Shuai (DCGM FIT BUT)
Zeinali Hossein, Ph.D. (DCGM FIT BUT)

URL

Keywords

speaker verification, NIST SRE, CMN, VAST, system fusion.

Abstract

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.

Published

2020

Pages

289-295

Journal

Proceedings of Odyssey: The Speaker and Language Recognition Workshop, vol. 2020, no. 11, ISSN 2312-2846

Proceedings

Proceedings of Odyssey 2020 The Speaker and Language Recognition Workshop

Conference

Odyssey 2020: The Speaker and Language Recognition Workshop, Tokyo, JP

Publisher

International Speech Communication Association

Place

Tokyo, JP

DOI

10.21437/Odyssey.2020-41

BibTeX

@INPROCEEDINGS{FITPUB12292,
   author = "Jahangir Alam and Gilles Boulianne and Luk\'{a}\v{s} Burget and Mohamed Dahmane and Mireia S\'{a}nchez Diez and Ond\v{r}ej Glembek and Marc Lalonde and Alicia D\'{i}ez Lozano and Pavel Mat\v{e}jka and Petr Mizera and Ladislav Mo\v{s}ner and C\'{e}dric Noiseux and Joao Monteiro and Ond\v{r}ej Novotn\'{y} and Old\v{r}ich Plchot and A. Johan Rohdin and Anna Silnova and Josef Slav\'{i}\v{c}ek and Themos Stafylakis and Pierre-Luc St-Charles and Shuai Wang and Hossein Zeinali",
   title = "Analysis of ABC Submission to NIST SRE 2019 CMN and VAST Challenge",
   pages = "289--295",
   booktitle = "Proceedings of Odyssey 2020 The Speaker and Language Recognition Workshop",
   journal = "Proceedings of Odyssey: The Speaker and Language Recognition Workshop",
   volume = 2020,
   number = 11,
   year = 2020,
   location = "Tokyo, JP",
   publisher = "International Speech Communication Association",
   ISSN = "2312-2846",
   doi = "10.21437/Odyssey.2020-41",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12292"
}