Publication Details
Calibration and Fusion of Query-by-example Systems - BUT SWS 2013
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Grézl František, Ing., Ph.D. (DCGM FIT BUT)
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
Ondel Yang Lucas Antoine Francois, Mgr., Ph.D. (DCGM FIT BUT)
query-by-example spoken term detection, acoustic keyword spotting, dynamic time warping, fusion, z-norm, m-norm, TWV
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.
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.
@INPROCEEDINGS{FITPUB10557, author = "Igor Sz\H{o}ke and Luk\'{a}\v{s} Burget and Franti\v{s}ek Gr\'{e}zl and Jan \v{C}ernock\'{y} and Francois Antoine Lucas Yang Ondel", title = "Calibration and Fusion of Query-by-example Systems - BUT SWS 2013", pages = "7899--7903", booktitle = "Proceedings of ICASSP 2014", year = 2014, location = "Florencie, IT", publisher = "IEEE Signal Processing Society", ISBN = "978-1-4799-2892-7", doi = "10.1109/ICASSP.2014.6855128", language = "english", url = "https://www.fit.vut.cz/research/publication/10557" }