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.
Cite as: Jancik, Z., Plchot, O., Brümmer, N., Burget, L., Glembek, O., Hubeika, V., Karafiat, M., Matejka, P., Mikolov, T., Strasheim, A., Cernocky, J.". (2010) Data selection and calibration issues in automatic language recognition - investigation with BUT-AGNITIO NIST LRE 2009 system. Proc. The Speaker and Language Recognition Workshop (Odyssey 2010), paper 37
@inproceedings{jancik10_odyssey,
author={Zdenek Jancik and Oldrich Plchot and Niko Brümmer and Lukas Burget and Ondrej Glembek and Valiantsina Hubeika and Martin Karafiat and Pavel Matejka and Tomas Mikolov and Albert Strasheim and Jan "Honza" Cernocky},
title={{Data selection and calibration issues in automatic language recognition - investigation with BUT-AGNITIO NIST LRE 2009 system}},
year=2010,
booktitle={Proc. The Speaker and Language Recognition Workshop (Odyssey 2010)},
pages={paper 37}
}