article · 2015
High performance Query-by-Example keyword spotting using Query-by-String techniques
Enrique Vidal, Alejandro H. Toselli, Joan Puigcerver
Cited by 16Abstract and details only
Abstract
Keyword Spotting (KWS) has been traditionally considered under two distinct frameworks: Query-by-Example (QbE) and Query-by-String (QbS). In both cases the user of the system wished to find occurrences of a particular keyword in a collection of document images. The difference is that, in QbE, the keyword is given as an exemplar image while, in QbS the keyword is given as a text string. In several works, the QbS scenario has been approached using QbE techniques; but the converse has not been studied in depth yet, despite of the fact that QbS systems typically achieve higher accuracy. In the present work, we present a very effective probabilistic approach to QbE KWS, based on highly accurate QbS KWS techniques which rely on models which need to be trained from annotated data. To assess the effectiveness of this approach, we tackle the segmentation-free QbE task of the ICFHR-2014 Competition on Handwritten KWS. Our approach achieves a mean average precision (mAP) as high as 0.715, which improves by more than 70% the best mAP achieved in this competition (0.419 under the same experimental conditions).
Cite this paper
Vidal, E., Toselli, A. H., & Puigcerver, J. (2015). High performance Query-by-Example keyword spotting using Query-by-String techniques. https://doi.org/10.1109/icdar.2015.7333860
Vidal, Enrique, et al. “High performance Query-by-Example keyword spotting using Query-by-String techniques.” 2015, pp. 741–45, https://doi.org/10.1109/icdar.2015.7333860.
Vidal, Enrique, Alejandro H. Toselli, and Joan Puigcerver. 2015. “High performance Query-by-Example keyword spotting using Query-by-String techniques.” https://doi.org/10.1109/icdar.2015.7333860.
Vidal, E., Toselli, A.H. and Puigcerver, J. (2015) ‘High performance Query-by-Example keyword spotting using Query-by-String techniques’. Available at: https://doi.org/10.1109/icdar.2015.7333860.
@article{vidal2015high,
title = {{High performance Query-by-Example keyword spotting using Query-by-String techniques}},
author = {Vidal, Enrique and Toselli, Alejandro H. and Puigcerver, Joan},
pages = {741--745},
year = {2015},
doi = {10.1109/icdar.2015.7333860}
}Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.
Related papers
An approach of keyword spotting based on HMM
Binfeng Yan, Rui Guo, Xiaoyan Zhu et al. · World Congress on Intelligent Control and Automation · 2002
Cited by 4
Broadcast Attention Learning for Real Telephone Speech Keyword Spotting
Dengfeng Ke, Baole Du, Yunjia Tong et al. · Journal of Physics Conference Series · 2023
Cited by 0Open access
Mutitask Learning Based Muti-examples Keywords Spotting in Low Resource Condition
Yang Jianbin, Kang Jian, Wei-Qiang Zhang et al. · International Conference on Signal Processing · 2018
Cited by 3
Speech Keyword Spotting with Rule Based Segmentation
Mindaugas Greibus, Laimutis Telksnys · Communications in computer and information science · 2013
Cited by 3
A Syllable Based Keyword Spotting System
Min Qin · Jisuanji gongcheng · 2004
Cited by 0
HMM-based Keyword Spotting System
WU Ya · Jisuanji gongcheng · 2004
Cited by 0