A Multi-feature Sets Fusion Strategy with Similar Samples Removal for Snore Sound Classification

Zhonghao Zhao; Yang Tan; Mengkai Sun; Yi Chang; Kun Qian; Bin Hu; Björn W. Schuller; Yoshiharu Yamamoto

doi:10.1007/978-981-99-2401-1_3

A Multi-feature Sets Fusion Strategy with Similar Samples Removal for Snore Sound Classification

Zhonghao Zhao, Yang Tan, Mengkai Sun, Yi Chang, Kun Qian^*, Bin Hu, Björn W. Schuller, Yoshiharu Yamamoto

^*Corresponding author for this work

School of Medical and Technology

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

Abstract

Obstructive sleep apnoe (OSA) is a common clinical sleep-related breathing disorder. Classifying the excitation location of snore sound can help doctors provide more accurate diagnosis and complete treatment plans. In this study, we propose a strategy to classify snore sound leveraging ‘classic’ features sets. At training stage, we eliminate selected samples to improve discrimination between different classes. As to unweighted average recall, a field’s major measure for imbalanced data, our method achieves 65.6 %, which significantly (p < 0.05, one-tailed z-test) outperforms the baseline of the INTERSPEECH 2017 ComParE Snoring Sub-challenge. Moreover, the proposed method can also improve the performance of other models based on the original classification results.

Original language	English
Title of host publication	Man-Machine Speech Communication - 17th National Conference, NCMMSC 2022, Proceedings
Editors	Ling Zhenhua, Gao Jianqing, Yu Kai, Jia Jia
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	30-43
Number of pages	14
ISBN (Print)	9789819924004
DOIs	https://doi.org/10.1007/978-981-99-2401-1_3
Publication status	Published - 2023
Event	17th National Conference on Man-Machine Speech Communication, NCMMSC 2022 - Hefei, China Duration: 15 Dec 2022 → 18 Dec 2022

Publication series

Name	Communications in Computer and Information Science
Volume	1765 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	17th National Conference on Man-Machine Speech Communication, NCMMSC 2022
Country/Territory	China
City	Hefei
Period	15/12/22 → 18/12/22

Keywords

Computer Audition
Digital Health
Feature Fusion
Obstructive Sleep Apnea
Snore Sound Classification

Access to Document

10.1007/978-981-99-2401-1_3

Cite this

Zhao, Z., Tan, Y., Sun, M., Chang, Y., Qian, K., Hu, B., Schuller, B. W., & Yamamoto, Y. (2023). A Multi-feature Sets Fusion Strategy with Similar Samples Removal for Snore Sound Classification. In L. Zhenhua, G. Jianqing, Y. Kai, & J. Jia (Eds.), Man-Machine Speech Communication - 17th National Conference, NCMMSC 2022, Proceedings (pp. 30-43). (Communications in Computer and Information Science; Vol. 1765 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-99-2401-1_3

Zhao, Zhonghao ; Tan, Yang ; Sun, Mengkai et al. / A Multi-feature Sets Fusion Strategy with Similar Samples Removal for Snore Sound Classification. Man-Machine Speech Communication - 17th National Conference, NCMMSC 2022, Proceedings. editor / Ling Zhenhua ; Gao Jianqing ; Yu Kai ; Jia Jia. Springer Science and Business Media Deutschland GmbH, 2023. pp. 30-43 (Communications in Computer and Information Science).

@inproceedings{87a0eecc4f534306bd72fdfd1bd0319a,

title = "A Multi-feature Sets Fusion Strategy with Similar Samples Removal for Snore Sound Classification",

abstract = "Obstructive sleep apnoe (OSA) is a common clinical sleep-related breathing disorder. Classifying the excitation location of snore sound can help doctors provide more accurate diagnosis and complete treatment plans. In this study, we propose a strategy to classify snore sound leveraging {\textquoteleft}classic{\textquoteright} features sets. At training stage, we eliminate selected samples to improve discrimination between different classes. As to unweighted average recall, a field{\textquoteright}s major measure for imbalanced data, our method achieves 65.6 %, which significantly (p < 0.05, one-tailed z-test) outperforms the baseline of the INTERSPEECH 2017 ComParE Snoring Sub-challenge. Moreover, the proposed method can also improve the performance of other models based on the original classification results.",

keywords = "Computer Audition, Digital Health, Feature Fusion, Obstructive Sleep Apnea, Snore Sound Classification",

author = "Zhonghao Zhao and Yang Tan and Mengkai Sun and Yi Chang and Kun Qian and Bin Hu and Schuller, {Bj{\"o}rn W.} and Yoshiharu Yamamoto",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 17th National Conference on Man-Machine Speech Communication, NCMMSC 2022 ; Conference date: 15-12-2022 Through 18-12-2022",

year = "2023",

doi = "10.1007/978-981-99-2401-1_3",

language = "English",

isbn = "9789819924004",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "30--43",

editor = "Ling Zhenhua and Gao Jianqing and Yu Kai and Jia Jia",

booktitle = "Man-Machine Speech Communication - 17th National Conference, NCMMSC 2022, Proceedings",

address = "Germany",

}

Zhao, Z, Tan, Y, Sun, M, Chang, Y, Qian, K , Hu, B, Schuller, BW & Yamamoto, Y 2023, A Multi-feature Sets Fusion Strategy with Similar Samples Removal for Snore Sound Classification. in L Zhenhua, G Jianqing, Y Kai & J Jia (eds), Man-Machine Speech Communication - 17th National Conference, NCMMSC 2022, Proceedings. Communications in Computer and Information Science, vol. 1765 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 30-43, 17th National Conference on Man-Machine Speech Communication, NCMMSC 2022, Hefei, China, 15/12/22. https://doi.org/10.1007/978-981-99-2401-1_3

A Multi-feature Sets Fusion Strategy with Similar Samples Removal for Snore Sound Classification. / Zhao, Zhonghao; Tan, Yang; Sun, Mengkai et al.
Man-Machine Speech Communication - 17th National Conference, NCMMSC 2022, Proceedings. ed. / Ling Zhenhua; Gao Jianqing; Yu Kai; Jia Jia. Springer Science and Business Media Deutschland GmbH, 2023. p. 30-43 (Communications in Computer and Information Science; Vol. 1765 CCIS).

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

TY - GEN

T1 - A Multi-feature Sets Fusion Strategy with Similar Samples Removal for Snore Sound Classification

AU - Zhao, Zhonghao

AU - Tan, Yang

AU - Sun, Mengkai

AU - Chang, Yi

AU - Qian, Kun

AU - Hu, Bin

AU - Schuller, Björn W.

AU - Yamamoto, Yoshiharu

PY - 2023

Y1 - 2023

N2 - Obstructive sleep apnoe (OSA) is a common clinical sleep-related breathing disorder. Classifying the excitation location of snore sound can help doctors provide more accurate diagnosis and complete treatment plans. In this study, we propose a strategy to classify snore sound leveraging ‘classic’ features sets. At training stage, we eliminate selected samples to improve discrimination between different classes. As to unweighted average recall, a field’s major measure for imbalanced data, our method achieves 65.6 %, which significantly (p < 0.05, one-tailed z-test) outperforms the baseline of the INTERSPEECH 2017 ComParE Snoring Sub-challenge. Moreover, the proposed method can also improve the performance of other models based on the original classification results.

AB - Obstructive sleep apnoe (OSA) is a common clinical sleep-related breathing disorder. Classifying the excitation location of snore sound can help doctors provide more accurate diagnosis and complete treatment plans. In this study, we propose a strategy to classify snore sound leveraging ‘classic’ features sets. At training stage, we eliminate selected samples to improve discrimination between different classes. As to unweighted average recall, a field’s major measure for imbalanced data, our method achieves 65.6 %, which significantly (p < 0.05, one-tailed z-test) outperforms the baseline of the INTERSPEECH 2017 ComParE Snoring Sub-challenge. Moreover, the proposed method can also improve the performance of other models based on the original classification results.

KW - Computer Audition

KW - Digital Health

KW - Feature Fusion

KW - Obstructive Sleep Apnea

KW - Snore Sound Classification

UR - http://www.scopus.com/inward/record.url?scp=85161495479&partnerID=8YFLogxK

U2 - 10.1007/978-981-99-2401-1_3

DO - 10.1007/978-981-99-2401-1_3

M3 - Conference contribution

AN - SCOPUS:85161495479

SN - 9789819924004

T3 - Communications in Computer and Information Science

SP - 30

EP - 43

BT - Man-Machine Speech Communication - 17th National Conference, NCMMSC 2022, Proceedings

A2 - Zhenhua, Ling

A2 - Jianqing, Gao

A2 - Kai, Yu

A2 - Jia, Jia

PB - Springer Science and Business Media Deutschland GmbH

T2 - 17th National Conference on Man-Machine Speech Communication, NCMMSC 2022

Y2 - 15 December 2022 through 18 December 2022

ER -

Zhao Z, Tan Y, Sun M, Chang Y, Qian K , Hu B et al. A Multi-feature Sets Fusion Strategy with Similar Samples Removal for Snore Sound Classification. In Zhenhua L, Jianqing G, Kai Y, Jia J, editors, Man-Machine Speech Communication - 17th National Conference, NCMMSC 2022, Proceedings. Springer Science and Business Media Deutschland GmbH. 2023. p. 30-43. (Communications in Computer and Information Science). doi: 10.1007/978-981-99-2401-1_3