Learning complementary representations via attention-based ensemble learning for cough-based COVID-19 recognition

authored by: Zhao Ren, Yi Chang, Wolfgang Nejdl, Björn W. Schuller
Abstract: Coughs sounds have shown promising as-potential marker for distinguishing COVID individuals from non-COVID ones. In this paper, we propose an attention-based ensemble learning approach to learn complementary representations from cough samples. Unlike most traditional schemes such as mere maxing or averaging, the proposed approach fairly considers the contribution of the representation generated by each single model. The attention mechanism is further investigated at the feature level and the decision level. Evaluated on the Track-1 test set of the DiCOVA challenge 2021, the experimental results demonstrate that the proposed feature-level attention-based ensemble learning achieves the best performance (Area Under Curve, AUC: 77.96%), resulting in an 8.05% improvement over the challenge baseline.
Organisation(s): L3S Research Centre
External Organisation(s): University of Augsburg
Imperial College London
Type: Article
Journal: Acta Acustica
Volume: 6
Publication date: 25.07.2022
Publication status: Published
Peer reviewed: Yes
ASJC Scopus subject areas: Acoustics and Ultrasonics, Computer Science Applications, Speech and Hearing, Electrical and Electronic Engineering
Electronic version(s): https://doi.org/10.1051/aacus/2022029 (Access: Open)
https://doi.org/10.15488/12807 (Access: Open)

BibTeX

@article{17417f9307e54fa2b243f34cacab2309,
title = "Learning complementary representations via attention-based ensemble learning for cough-based COVID-19 recognition",
abstract = "Coughs sounds have shown promising as-potential marker for distinguishing COVID individuals from non-COVID ones. In this paper, we propose an attention-based ensemble learning approach to learn complementary representations from cough samples. Unlike most traditional schemes such as mere maxing or averaging, the proposed approach fairly considers the contribution of the representation generated by each single model. The attention mechanism is further investigated at the feature level and the decision level. Evaluated on the Track-1 test set of the DiCOVA challenge 2021, the experimental results demonstrate that the proposed feature-level attention-based ensemble learning achieves the best performance (Area Under Curve, AUC: 77.96%), resulting in an 8.05% improvement over the challenge baseline.",
keywords = "Attention mechanism, Complementary representation, Cough sound, COVID-19, Ensemble learning",
author = "Zhao Ren and Yi Chang and Wolfgang Nejdl and Schuller, {Bj{\"o}rn W.}",
note = "Funding Information: This work was partially supported by the BMBF project LeibnizKILabor with grant No. 01DD20003, and the Horizon H2020 Marie Sk{\~o}{\~o}lodowska-Curie Actions Initial Training Network European Training Network (MSCA-ITN-ETN) project under grant agreement No. 766287 (TAPAS). The authors would thank the friendly discussions from their colleagues Lukas Stappen and Vincent Karas. ",
year = "2022",
month = jul,
day = "25",
doi = "10.1051/aacus/2022029",
language = "English",
volume = "6",
journal = "Acta Acustica",
issn = "2681-4617",
publisher = "EDP Sciences",
number = "29",
}