Publication Details
Coping with Channel Mismatch in Query-By-Example - BUT QUESST 2014
Skácel Miroslav, Ing.
Černocký Jan, prof. Dr. Ing. (DCGM)
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
query-by-example spoken term detection, spoken document retrieval, acoustic keyword spotting, dynamic time warping, fusion, m-norm, logistic regression
This article is about Coping with Channel Mismatch in Query-By-Example - BUT QUESST 2014. It regards a spoken term detection technique with queries entered by voice.
The paper investigates into Query by Example (QbE) - a spoken term detection technique with queries entered by voice. It describes BUT QbE system that achieved the best accuracy in MediaEval QUESST2014 evaluations. This evaluation was challenging because of severe mismatch between queries and utterances, and introduction of new types of queries. The paper provides an analysis of DTW sub-system’s in mismatched conditions (especially targeting DTW metrics) and discusses approaches investigated for QUESST2014: generation of calibration side-information by a language identification system, and handling T2 and T3 queries relaxing the constraints of an exact match. All results are provided on QUESST2014 development and evaluation data
@inproceedings{BUT119899,
author="Igor {Szőke} and Miroslav {Skácel} and Jan {Černocký} and Lukáš {Burget}",
title="Coping with Channel Mismatch in Query-By-Example - BUT QUESST 2014",
booktitle="Proceedings of 2015 IEEE International Conference on Acoustics, Speech and Signal Processing",
year="2015",
pages="5838--5842",
publisher="IEEE Signal Processing Society",
address="South Brisbane, Queensland",
doi="10.1109/ICASSP.2015.7179091",
isbn="978-1-4673-6997-8",
url="https://www.fit.vut.cz/research/publication/10956/"
}