Faculty of Information Technology, BUT

Publication Details

BUT-AGNITIO System Description for NIST Language Recognition Evaluation 2009

BRÜMMER Niko, BURGET Lukáš, GLEMBEK Ondřej, HUBEIKA Valiantsina, JANČÍK Zdeněk, KARAFIÁT Martin, MATĚJKA Pavel, MIKOLOV Tomáš, PLCHOT Oldřich and STRASHEIM Albert. BUT-AGNITIO System Description for NIST Language Recognition Evaluation 2009. In: Proceedings NIST 2009 Language Recognition Evaluation Workshop. Baltimore, Maryland, USA: National Institute of Standards and Technology, 2009, pp. 1-7.
Czech title
Popis VUT-Agnition systému pro NIST LRE 2009 Workshop
Type
conference paper
Language
english
Authors
Brümmer Niko (Agnitio)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Glembek Ondřej, Ing., Ph.D. (DCGM FIT BUT)
Hubeika Valiantsina, Ing. (DCGM FIT BUT)
Jančík Zdeněk, Ing. (DCGM FIT BUT)
Karafiát Martin, Ing., Ph.D. (DCGM FIT BUT)
Matějka Pavel, Ing., Ph.D. (DCGM FIT BUT)
Mikolov Tomáš, Ing. (DCGM FIT BUT)
Plchot Oldřich, Ing., Ph.D. (DCGM FIT BUT)
Strasheim Albert (USB)
URL
Keywords
speech, language recognition, evaluation
Abstract
The paper is on four different systems that were presented at the NIST 2009 LRE Workshop in Baltimore. Systems were produced in cooperation between BUT and Agnitio research teams.
Annotation
BUT-AGNITIO are submitting 4 different systems, which we exercised on the closed-set, open-set and language-pairs tasks. Here we list these systems and specify which system should be considered as primary system for which task. Detailed descriptions follow later. BUT-AGN-1: This is our primary system for closed-set. See section 6.1 for details. BUT-AGN-2: This is our primary system for open-set. It was also exercised on closed-set as a contrastive system. See section 6.2 for details. BUT-AGN-3: This is our primary system for language-pairs. It was also exercised on closed-set as a contrastive system. See section 6.3 for details. BUT-AGN-4: This is a contrastive system for closed-set. See section 6.4 for details. For all of our systems, the score in every trial may be interpreted as the log-likelihood-ratio for the target versus the non-target hypothesis.
Published
2009
Pages
1-7
Proceedings
Proceedings NIST 2009 Language Recognition Evaluation Workshop
Conference
The 2009 NIST Language Recognition, Baltimore, US
Publisher
National Institute of Standards and Technology
Place
Baltimore, Maryland, USA, US
BibTeX
@INPROCEEDINGS{FITPUB9551,
   author = "Niko Br\"{u}mmer and Luk\'{a}\v{s} Burget and Ond\v{r}ej Glembek and Valiantsina Hubeika and Zden\v{e}k Jan\v{c}\'{i}k and Martin Karafi\'{a}t and Pavel Mat\v{e}jka and Tom\'{a}\v{s} Mikolov and Old\v{r}ich Plchot and Albert Strasheim",
   title = "BUT-AGNITIO System Description for NIST Language Recognition Evaluation 2009",
   pages = "1--7",
   booktitle = "Proceedings NIST 2009 Language Recognition Evaluation Workshop",
   year = 2009,
   location = "Baltimore, Maryland, USA, US",
   publisher = "National Institute of Standards and Technology",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/9551"
}
Back to top