CoughLIME: Sonified Explanations for the Predictions of COVID-19 Cough Classifiers

Anne Wullenweber; Alican Akman; Bjorn W. Schuller

doi:10.1109/EMBC48229.2022.9871291

CoughLIME: Sonified Explanations for the Predictions of COVID-19 Cough Classifiers

Anne Wullenweber
, Alican Akman
, Bjorn W. Schuller

Imperial College London
Technical University of Munich
University Hospital Augsburg

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

18 Scopus citations

Abstract

Since the emergence of the COVID-19 pandemic, various methods to detect the illness from cough and speech audio data have been proposed. While many of them deliver promising results, they lack transparency in the form of expla-nations which is crucial for establishing trust in the classifiers. We propose CoughLIME which extends LIME to explanations for audio data, specifically tailored towards cough data. We show that CoughLIME is capable of generating faithful sonified explanations for COVID-19 detection. To quantify the performance of the explanations generated for the CIdeR model, we adopt pixel flipping to audio and introduce a novel metric to assess the performance of the XAI classifier. CoughLIME achieves a ΔAUC of 19.48 % generating explanations for CIdeR's predictions.

Original language	English
Title of host publication	44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1342-1345
Number of pages	4
ISBN (Electronic)	9781728127828
DOIs	https://doi.org/10.1109/EMBC48229.2022.9871291
State	Published - 2022
Externally published	Yes
Event	44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022 - Glasgow, United Kingdom Duration: 11 Jul 2022 → 15 Jul 2022

Publication series

Name	Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Volume	2022-July
ISSN (Print)	1557-170X

Conference

Conference	44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022
Country/Territory	United Kingdom
City	Glasgow
Period	11/07/22 → 15/07/22

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Access to Document

10.1109/EMBC48229.2022.9871291

Cite this

Wullenweber, A., Akman, A., & Schuller, B. W. (2022). CoughLIME: Sonified Explanations for the Predictions of COVID-19 Cough Classifiers. In 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022 (pp. 1342-1345). (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS; Vol. 2022-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC48229.2022.9871291

Wullenweber, Anne ; Akman, Alican ; Schuller, Bjorn W. / CoughLIME : Sonified Explanations for the Predictions of COVID-19 Cough Classifiers. 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 1342-1345 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).

@inproceedings{401a3feca9d342bf95f3a932e8bf124d,

title = "CoughLIME: Sonified Explanations for the Predictions of COVID-19 Cough Classifiers",

abstract = "Since the emergence of the COVID-19 pandemic, various methods to detect the illness from cough and speech audio data have been proposed. While many of them deliver promising results, they lack transparency in the form of expla-nations which is crucial for establishing trust in the classifiers. We propose CoughLIME which extends LIME to explanations for audio data, specifically tailored towards cough data. We show that CoughLIME is capable of generating faithful sonified explanations for COVID-19 detection. To quantify the performance of the explanations generated for the CIdeR model, we adopt pixel flipping to audio and introduce a novel metric to assess the performance of the XAI classifier. CoughLIME achieves a ΔAUC of 19.48 \% generating explanations for CIdeR's predictions.",

author = "Anne Wullenweber and Alican Akman and Schuller, \{Bjorn W.\}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022 ; Conference date: 11-07-2022 Through 15-07-2022",

year = "2022",

doi = "10.1109/EMBC48229.2022.9871291",

language = "English",

series = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1342--1345",

booktitle = "44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022",

}

Wullenweber, A, Akman, A & Schuller, BW 2022, CoughLIME: Sonified Explanations for the Predictions of COVID-19 Cough Classifiers. in 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, vol. 2022-July, Institute of Electrical and Electronics Engineers Inc., pp. 1342-1345, 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022, Glasgow, United Kingdom, 11/07/22. https://doi.org/10.1109/EMBC48229.2022.9871291

CoughLIME: Sonified Explanations for the Predictions of COVID-19 Cough Classifiers. / Wullenweber, Anne; Akman, Alican; Schuller, Bjorn W.
44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 1342-1345 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS; Vol. 2022-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - CoughLIME

T2 - 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022

AU - Wullenweber, Anne

AU - Akman, Alican

AU - Schuller, Bjorn W.

PY - 2022

Y1 - 2022

N2 - Since the emergence of the COVID-19 pandemic, various methods to detect the illness from cough and speech audio data have been proposed. While many of them deliver promising results, they lack transparency in the form of expla-nations which is crucial for establishing trust in the classifiers. We propose CoughLIME which extends LIME to explanations for audio data, specifically tailored towards cough data. We show that CoughLIME is capable of generating faithful sonified explanations for COVID-19 detection. To quantify the performance of the explanations generated for the CIdeR model, we adopt pixel flipping to audio and introduce a novel metric to assess the performance of the XAI classifier. CoughLIME achieves a ΔAUC of 19.48 % generating explanations for CIdeR's predictions.

AB - Since the emergence of the COVID-19 pandemic, various methods to detect the illness from cough and speech audio data have been proposed. While many of them deliver promising results, they lack transparency in the form of expla-nations which is crucial for establishing trust in the classifiers. We propose CoughLIME which extends LIME to explanations for audio data, specifically tailored towards cough data. We show that CoughLIME is capable of generating faithful sonified explanations for COVID-19 detection. To quantify the performance of the explanations generated for the CIdeR model, we adopt pixel flipping to audio and introduce a novel metric to assess the performance of the XAI classifier. CoughLIME achieves a ΔAUC of 19.48 % generating explanations for CIdeR's predictions.

UR - https://www.scopus.com/pages/publications/85138127968

U2 - 10.1109/EMBC48229.2022.9871291

DO - 10.1109/EMBC48229.2022.9871291

M3 - Conference contribution

C2 - 36086189

AN - SCOPUS:85138127968

T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

SP - 1342

EP - 1345

BT - 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 11 July 2022 through 15 July 2022

ER -

Wullenweber A, Akman A, Schuller BW. CoughLIME: Sonified Explanations for the Predictions of COVID-19 Cough Classifiers. In 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 1342-1345. (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). doi: 10.1109/EMBC48229.2022.9871291

CoughLIME: Sonified Explanations for the Predictions of COVID-19 Cough Classifiers

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this