Publication Details

Data selection and calibration issues in automatic language recognition - investigation with BUT-AGNITIO NIST LRE 2009 system

JANČÍK, Z.; PLCHOT, O.; BRUMMER, J.; BURGET, L.; GLEMBEK, O.; HUBEIKA, V.; KARAFIÁT, M.; MATĚJKA, P.; MIKOLOV, T.; STRASHEIM, A.; ČERNOCKÝ, J. Data selection and calibration issues in automatic language recognition - investigation with BUT-AGNITIO NIST LRE 2009 system. In Proc. Odyssey 2010 - The Speaker and Language Recognition Workshop. Brno: International Speech Communication Association, 2010. p. 215-221. ISBN: 978-80-214-4114-9.
Czech title
Problematika výběru dat a kalibrace v automatickém rozpoznávání jazyka - výzkum s BUT-AGNITIO systémem pro NIST LRE 2009
Type
conference paper
Language
English
Authors
Jančík Zdeněk, Ing.
Plchot Oldřich, Ing., Ph.D. (DCGM)
Brummer Johan Nikolaas Langenhoven, Dr.
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Glembek Ondřej, Ing., Ph.D.
Hubeika Valiantsina, Ing.
Karafiát Martin, Ing., Ph.D. (DCGM)
Matějka Pavel, Ing., Ph.D. (DCGM)
Mikolov Tomáš, Ing., Ph.D.
Strasheim Albeert
Černocký Jan, prof. Dr. Ing. (DCGM)
URL
Keywords

speech, automatic, language, recognition, evaluation

Abstract

This paper is on data selection and calibration issues in automatic language recognition. The paper is based on investigation with BUT-AGNITIO NIST LRE 2009 system.

Annotation

This paper summarizes the BUT-AGNITIO system for NIST Language Recognition Evaluation 2009. The post-evaluation analysis aimed mainly at improving the quality of the data (fixing language label problems and detecting overlapping speakers in the training and development sets) and investigation of different compositions of the development set. The paper further investigates into JFA-based acoustic system and reports results for new SVM-PCA systems going beyond BUT-Agnitio original NIST LRE 2009 submission. All results are presented on evaluation data from NIST LRE 2009 task.

Published
2010
Pages
215–221
Proceedings
Proc. Odyssey 2010 - The Speaker and Language Recognition Workshop
ISBN
978-80-214-4114-9
Publisher
International Speech Communication Association
Place
Brno
EID Scopus
BibTeX
@inproceedings{BUT34924,
  author="Zdeněk {Jančík} and Oldřich {Plchot} and Johan Nikolaas Langenhoven {Brummer} and Lukáš {Burget} and Ondřej {Glembek} and Valiantsina {Hubeika} and Martin {Karafiát} and Pavel {Matějka} and Tomáš {Mikolov} and Albeert {Strasheim} and Jan {Černocký}",
  title="Data selection and calibration issues in automatic language recognition - investigation with BUT-AGNITIO NIST LRE 2009 system",
  booktitle="Proc. Odyssey 2010 - The Speaker and Language Recognition Workshop",
  year="2010",
  pages="215--221",
  publisher="International Speech Communication Association",
  address="Brno",
  isbn="978-80-214-4114-9",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2010/jancik_odys2010.pdf"
}
Back to top