Publication Details

Calibration and Fusion of Query-by-example Systems - BUT SWS 2013

SZŐKE, I.; BURGET, L.; GRÉZL, F.; ČERNOCKÝ, J.; ONDEL YANG, L. Calibration and Fusion of Query-by-example Systems - BUT SWS 2013. In Proceedings of ICASSP 2014. Florencie: IEEE Signal Processing Society, 2014. p. 7899-7903. ISBN: 978-1-4799-2892-7.
Czech title
Kalibrace a fúze systémů pro vyhledávání pomocí mluvených dotazů - BUT SWS 2013
Type
conference paper
Language
English
Authors
URL
Keywords

query-by-example spoken term detection, acoustic keyword spotting, dynamic time warping, fusion, z-norm, m-norm, TWV

Abstract

In this paper we performed a comparison of AKWS and DTW approaches with several phone-posterior generators for QbE in several languages. We found the proposed m-norm a really promising way of score normalization of QbE systems.

Annotation

This paper summarizes our work for MediaEval 2013 Spoken Web Search task evaluations. The task was Query-by-Example (search of spoken queries within spoken data). We submitted a system composed of 26 subsystems, of which 13 are based on Acoustic Keyword Spotting and 13 on Dynamic Time Warping. All of them use threestate phoneme posteriors as input features. Our main contribution was m-norm normalization of particular subsystems together with the fusion based on binary logistic regression. The results, including per-language analysis, are provided on MediaEval 2013 dataset.

Published
2014
Pages
7899–7903
Proceedings
Proceedings of ICASSP 2014
ISBN
978-1-4799-2892-7
Publisher
IEEE Signal Processing Society
Place
Florencie
DOI
UT WoS
000343655307178
EID Scopus
BibTeX
@inproceedings{BUT111545,
  author="Igor {Szőke} and Lukáš {Burget} and František {Grézl} and Jan {Černocký} and Lucas Antoine Francois {Ondel}",
  title="Calibration and Fusion of Query-by-example Systems - BUT SWS 2013",
  booktitle="Proceedings of ICASSP 2014",
  year="2014",
  pages="7899--7903",
  publisher="IEEE Signal Processing Society",
  address="Florencie",
  doi="10.1109/ICASSP.2014.6855128",
  isbn="978-1-4799-2892-7",
  url="https://www.fit.vut.cz/research/publication/10557/"
}
Files
Back to top