Článek ve sborníku konference

BRÜMMER Niko, BURGET Lukáš, GLEMBEK Ondřej, HUBEIKA Valiantsina, JANČÍK Zdeněk, KARAFIÁT Martin, MATĚJKA Pavel, MIKOLOV Tomáš, PLCHOT Oldřich a STRASHEIM Albert. BUT-AGNITIO System Description for NIST Language Recognition Evaluation 2009. In: Proceedings NIST 2009 Language Recognition Evaluation Workshop. Baltimore, Maryland, USA: United States Department of Commerce, National Institute of Standards and Technology, 2009, s. 1-7.
Jazyk publikace:angličtina
Název publikace:BUT-AGNITIO System Description for NIST Language Recognition Evaluation 2009
Název (cs):Popis VUT-Agnition systému pro NIST LRE 2009 Workshop
Strany:1-7
Sborník:Proceedings NIST 2009 Language Recognition Evaluation Workshop
Konference:The 2009 NIST Language Recognition
Místo vydání:Baltimore, Maryland, USA, US
Rok:2009
Vydavatel:United States Department of Commerce, National Institute of Standards and Technology
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2009/brummer_BUT_AGNITIO_LRE09_SYSD.pdf [PDF]
Klíčová slova
speech, language recognition, evaluation
Anotace
Článek pojednává o čtyřech různých systémech, které byly presentovány na NIST 2009 LRE Workshopu v Baltimore, USA. Systémy byly vytvořeny ve spolupráci mezi vědeckými týmy VUT a společnosti Agnitio.
Abstrakt
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.
BibTeX:
@INPROCEEDINGS{
   author = {Niko Brümmer and Lukáš Burget and Ondřej Glembek and
	Valiantsina Hubeika and Zdeněk Jančík and Martin Karafiát
	and Pavel Matějka and Tomáš Mikolov and Oldřich 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 = {http://www.fit.vutbr.cz/research/view_pub.php.cs?id=9551}
}

Vaše IPv4 adresa: 54.205.105.23
Přepnout na IPv6 spojení

DNSSEC [dnssec]