Result Details

Discriminative Semi-supervised Training for Keyword Search in Low Resource Languages

HSIAO, R.; NG, T.; GRÉZL, F.; KARAKOS, D.; TSAKALIDIS, S.; NGUYEN, L.; SCHWARTZ, R. Discriminative Semi-supervised Training for Keyword Search in Low Resource Languages. Proceedings of ASRU 2013. Olomouc: IEEE Signal Processing Society, 2013. p. 440-445. ISBN: 978-1-4799-2755-5.
Type
conference paper
Language
English
Authors
Hsiao Roger
Ng Tim
Grézl František, Ing., Ph.D., DCGM (FIT)
Karakos Damianos
Tsakalidis Stavros
Nguyen Long
Schwartz Richard
Abstract

This article is about Discriminative Semi-supervised Training for Keyword Search in Low Resource Languages.

Keywords

semi-supervised training, low resourcelanguages, keyword spotting

URL
Annotation

In this paper, we investigate semi-supervised training for low resource languages where the initial systems may have high error rate ( 70.0% word eror rate). To handle the lack of data, we study semi-supervised techniques including data selection, data weighting, discriminative training and multilayer perceptron learning to improve system performance. The entire suite of semi-supervised methods presented in this paper was evaluated under the IARPA Babel program for the keyword spotting tasks. Our semi-supervised system had the best performance in the OpenKWS13 surprise language evaluation for the limited condition. In this paper, we describe our work on the Turkish and Vietnamese systems.

Published
2013
Pages
440–445
Proceedings
Proceedings of ASRU 2013
Conference
IEEE 2013 Workshop on Automatic Speech Recognition and Understanding
ISBN
978-1-4799-2755-5
Publisher
IEEE Signal Processing Society
Place
Olomouc
BibTeX 
@inproceedings{BUT105975,
  author="Roger {Hsiao} and Tim {Ng} and František {Grézl} and Damianos {Karakos} and Stavros {Tsakalidis} and Long {Nguyen} and Richard {Schwartz}",
  title="Discriminative Semi-supervised Training for Keyword Search in Low Resource Languages",
  booktitle="Proceedings of ASRU 2013",
  year="2013",
  pages="440--445",
  publisher="IEEE Signal Processing Society",
  address="Olomouc",
  isbn="978-1-4799-2755-5",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2013/hsiao_asru2013_0000440.pdf"
}
Projects
IARPA Building Speech Recognition for Keyword Search in a New Language in a Week with Limited Training Data (BABEL) - Babelon, BBN, start: 2012-03-05, end: 2016-11-04, completed
Security-Oriented Research in Information Technology, MŠMT, Institucionální prostředky SR ČR (např. VZ, VC), MSM0021630528, start: 2007-01-01, end: 2013-12-31, running
Research groups
Speech Data Mining Research Group BUT Speech@FIT (RG SPEECH)
Departments
Department of Computer Graphics and Multimedia (DCGM)
Back to top