Calibration and fusion of query-by-example systems — But SWS 2013

Author

Szoke, Igor ; Burget, Lukas ; Grezl, Frantisek ; Cernocky, Jan Honza ; Ondel, Lucas

Author_Institution

BUT Speech@FIT, Brno Univ. of Technol., Brno, Czech Republic

fYear

2014

fDate

4-9 May 2014

Firstpage

7849

Lastpage

7853

Abstract

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 three-state 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.

Keywords

acoustic signal processing; natural language processing; query processing; regression analysis; speech processing; MediaEval 2013 Spoken Web Search task evaluations; MediaEval 2013 dataset; SWS 2013; acoustic keyword spotting; binary logistic regression; dynamic time warping; m-norm normalization; per-language analysis; query-by-example systems; three-state phoneme posteriors; Acoustics; Artificial neural networks; Calibration; Conferences; Databases; Speech; Web search; TWV; acoustic keyword spotting; dynamic time warping; fusion; m-norm; query-by-example spoken term detection; z-norm;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on

Conference_Location

Florence

Type

conf

DOI

10.1109/ICASSP.2014.6855128

Filename

6855128