Snore Sound Recognition via an Explainable Capsule Network

Min Ki Cho; Zhonghao Zhao; Zhihua Wang; Kun Qian; Bin Hu; Yoshiharu Yamamoto; Björn W. Schuller

doi:10.1109/GCCE59613.2023.10315619

Snore Sound Recognition via an Explainable Capsule Network

Min Ki Cho, Zhonghao Zhao, Zhihua Wang, Kun Qian^*, Bin Hu^*, Yoshiharu Yamamoto, Björn W. Schuller

^*此作品的通讯作者

医学技术学院

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

1 引用（Scopus）

摘要

Snoring can be caused by an upper airway reaction while sleeping. Classifying the excitation locations of snore sounds accurately provides assistance for treating snoring. In this research, we propose a convolutional neural network combined with a Capsule Network (CapsNet) to solve this problem. The models were trained and tested on the Munich-Passau Snore Sound Corpus (MPSSC), a relatively small and imbalanced dataset that contains four classes. As a result, the proposed method achieved an Unweighted Average Recall (UAR) of 58.5 %. Furthermore, we explained the working principle of the CapsNet through visualization, which could be helpful for understanding the generation of the results.

源语言	英语
主期刊名	GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics
出版商	Institute of Electrical and Electronics Engineers Inc.
页	1048-1049
页数	2
ISBN（电子版）	9798350340181
DOI	https://doi.org/10.1109/GCCE59613.2023.10315619
出版状态	已出版 - 2023
活动	12th IEEE Global Conference on Consumer Electronics, GCCE 2023 - Nara, 日本期限: 10 10月 2023 → 13 10月 2023

出版系列

姓名	GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics

会议

会议	12th IEEE Global Conference on Consumer Electronics, GCCE 2023
国家/地区	日本
市	Nara
时期	10/10/23 → 13/10/23

访问文件

10.1109/GCCE59613.2023.10315619

其它文件与链接

链接到 Scopus 的出版物

引用此

Cho, M. K., Zhao, Z., Wang, Z., Qian, K., Hu, B., Yamamoto, Y., & Schuller, B. W. (2023). Snore Sound Recognition via an Explainable Capsule Network. 在 GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics (页码 1048-1049). (GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GCCE59613.2023.10315619

@inproceedings{1cd2c30b3d574a2a89e4cc9d4fcd341c,

title = "Snore Sound Recognition via an Explainable Capsule Network",

abstract = "Snoring can be caused by an upper airway reaction while sleeping. Classifying the excitation locations of snore sounds accurately provides assistance for treating snoring. In this research, we propose a convolutional neural network combined with a Capsule Network (CapsNet) to solve this problem. The models were trained and tested on the Munich-Passau Snore Sound Corpus (MPSSC), a relatively small and imbalanced dataset that contains four classes. As a result, the proposed method achieved an Unweighted Average Recall (UAR) of 58.5 %. Furthermore, we explained the working principle of the CapsNet through visualization, which could be helpful for understanding the generation of the results.",

keywords = "Capsule Network, Computer Audition, Digital Health, Explainable Model, Snore Sound Classification",

author = "Cho, {Min Ki} and Zhonghao Zhao and Zhihua Wang and Kun Qian and Bin Hu and Yoshiharu Yamamoto and Schuller, {Bj{\"o}rn W.}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 12th IEEE Global Conference on Consumer Electronics, GCCE 2023 ; Conference date: 10-10-2023 Through 13-10-2023",

year = "2023",

doi = "10.1109/GCCE59613.2023.10315619",

language = "English",

series = "GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics",

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

pages = "1048--1049",

booktitle = "GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics",

address = "United States",

}

Cho, MK, Zhao, Z, Wang, Z, Qian, K, Hu, B, Yamamoto, Y & Schuller, BW 2023, Snore Sound Recognition via an Explainable Capsule Network. 在 GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics. GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics, Institute of Electrical and Electronics Engineers Inc., 页码 1048-1049, 12th IEEE Global Conference on Consumer Electronics, GCCE 2023, Nara, 日本, 10/10/23. https://doi.org/10.1109/GCCE59613.2023.10315619

Snore Sound Recognition via an Explainable Capsule Network. / Cho, Min Ki; Zhao, Zhonghao; Wang, Zhihua 等.
GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics. Institute of Electrical and Electronics Engineers Inc., 2023. 页码 1048-1049 (GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics).

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

TY - GEN

T1 - Snore Sound Recognition via an Explainable Capsule Network

AU - Cho, Min Ki

AU - Zhao, Zhonghao

AU - Wang, Zhihua

AU - Qian, Kun

AU - Hu, Bin

AU - Yamamoto, Yoshiharu

AU - Schuller, Björn W.

PY - 2023

Y1 - 2023

N2 - Snoring can be caused by an upper airway reaction while sleeping. Classifying the excitation locations of snore sounds accurately provides assistance for treating snoring. In this research, we propose a convolutional neural network combined with a Capsule Network (CapsNet) to solve this problem. The models were trained and tested on the Munich-Passau Snore Sound Corpus (MPSSC), a relatively small and imbalanced dataset that contains four classes. As a result, the proposed method achieved an Unweighted Average Recall (UAR) of 58.5 %. Furthermore, we explained the working principle of the CapsNet through visualization, which could be helpful for understanding the generation of the results.

AB - Snoring can be caused by an upper airway reaction while sleeping. Classifying the excitation locations of snore sounds accurately provides assistance for treating snoring. In this research, we propose a convolutional neural network combined with a Capsule Network (CapsNet) to solve this problem. The models were trained and tested on the Munich-Passau Snore Sound Corpus (MPSSC), a relatively small and imbalanced dataset that contains four classes. As a result, the proposed method achieved an Unweighted Average Recall (UAR) of 58.5 %. Furthermore, we explained the working principle of the CapsNet through visualization, which could be helpful for understanding the generation of the results.

KW - Capsule Network

KW - Computer Audition

KW - Digital Health

KW - Explainable Model

KW - Snore Sound Classification

UR - http://www.scopus.com/inward/record.url?scp=85179760677&partnerID=8YFLogxK

U2 - 10.1109/GCCE59613.2023.10315619

DO - 10.1109/GCCE59613.2023.10315619

M3 - Conference contribution

AN - SCOPUS:85179760677

T3 - GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics

SP - 1048

EP - 1049

BT - GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th IEEE Global Conference on Consumer Electronics, GCCE 2023

Y2 - 10 October 2023 through 13 October 2023

ER -

Cho MK, Zhao Z, Wang Z, Qian K, Hu B, Yamamoto Y 等. Snore Sound Recognition via an Explainable Capsule Network. 在 GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics. Institute of Electrical and Electronics Engineers Inc. 2023. 页码 1048-1049. (GCCE 2023 - 2023 IEEE 12th Global Conference on Consumer Electronics). doi: 10.1109/GCCE59613.2023.10315619

Snore Sound Recognition via an Explainable Capsule Network

摘要

出版系列

会议

访问文件

其它文件与链接

指纹

引用此