Detection of mild dyspnea from pairs of speech recordings

Sander Boelders; Venkata Srikanth Nallanthighal; Vlado Menkovski; Aki Härmä

doi:10.1109/ICASSP40776.2020.9054751

Detection of mild dyspnea from pairs of speech recordings

Sander Boelders^*, Venkata Srikanth Nallanthighal, Vlado Menkovski, Aki Härmä

^*Corresponding author for this work

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

Abstract

Shortness of breath, or dyspnea is a condition of the cardiopulmonary system that may be caused by, for example, a heart or lung disease, or physical load. In this paper, we explore techniques of detecting mild dyspnea directly from conversational speech, for example, in a telehealth application. We demonstrate with a collection of speech recordings before and after a light physical exercise that a siamese neural network, when presented examples of the two conditions, can detect the difference between two speech signals. This shows that this signal can be detected using data-pairs, removing the need for ratings of severity or the distinction of separate classes.

Original language	English
Title of host publication	2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
Publisher	IEEE
Pages	4102-4106
Number of pages	5
ISBN (Electronic)	9781509066315
DOIs	https://doi.org/10.1109/ICASSP40776.2020.9054751
Publication status	Published - May 2020
Externally published	Yes
Event	45th International Conference on Acoustics, Speech, and Signal Processing - Online, Barcelona, Spain Duration: 4 May 2020 → 8 May 2020 Conference number: 45 https://2020.ieeeicassp.org/

Publication series

Series	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	2020-May
ISSN	1520-6149

Conference

Conference	45th International Conference on Acoustics, Speech, and Signal Processing
Abbreviated title	ICASSP 2020
Country/Territory	Spain
City	Barcelona
Period	4/05/20 → 8/05/20
Internet address	https://2020.ieeeicassp.org/

Keywords

Data pairs
Deeplearning
Dyspnea
Health monitoring
Speech signal processing

Access to Document

10.1109/ICASSP40776.2020.9054751

Cite this

Boelders, Sander ; Nallanthighal, Venkata Srikanth ; Menkovski, Vlado et al. / Detection of mild dyspnea from pairs of speech recordings. 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings. IEEE, 2020. pp. 4102-4106 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Vol. 2020-May).

@inproceedings{f38b032d0aa44c13942107c6d0580476,

title = "Detection of mild dyspnea from pairs of speech recordings",

abstract = "Shortness of breath, or dyspnea is a condition of the cardiopulmonary system that may be caused by, for example, a heart or lung disease, or physical load. In this paper, we explore techniques of detecting mild dyspnea directly from conversational speech, for example, in a telehealth application. We demonstrate with a collection of speech recordings before and after a light physical exercise that a siamese neural network, when presented examples of the two conditions, can detect the difference between two speech signals. This shows that this signal can be detected using data-pairs, removing the need for ratings of severity or the distinction of separate classes.",

keywords = "Data pairs, Deeplearning, Dyspnea, Health monitoring, Speech signal processing",

author = "Sander Boelders and Nallanthighal, {Venkata Srikanth} and Vlado Menkovski and Aki H{\"a}rm{\"a}",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 45th International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 ; Conference date: 04-05-2020 Through 08-05-2020",

year = "2020",

month = may,

doi = "10.1109/ICASSP40776.2020.9054751",

language = "English",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

publisher = "IEEE",

pages = "4102--4106",

booktitle = "2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings",

address = "United States",

url = "https://2020.ieeeicassp.org/",

}

Boelders, S, Nallanthighal, VS, Menkovski, V & Härmä, A 2020, Detection of mild dyspnea from pairs of speech recordings. in 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings., 9054751, IEEE, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2020-May, pp. 4102-4106, 45th International Conference on Acoustics, Speech, and Signal Processing, Barcelona, Spain, 4/05/20. https://doi.org/10.1109/ICASSP40776.2020.9054751

Detection of mild dyspnea from pairs of speech recordings. / Boelders, Sander; Nallanthighal, Venkata Srikanth; Menkovski, Vlado et al.
2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings. IEEE, 2020. p. 4102-4106 9054751 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Vol. 2020-May).

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

TY - GEN

T1 - Detection of mild dyspnea from pairs of speech recordings

AU - Boelders, Sander

AU - Nallanthighal, Venkata Srikanth

AU - Menkovski, Vlado

AU - Härmä, Aki

N1 - Conference code: 45

PY - 2020/5

Y1 - 2020/5

N2 - Shortness of breath, or dyspnea is a condition of the cardiopulmonary system that may be caused by, for example, a heart or lung disease, or physical load. In this paper, we explore techniques of detecting mild dyspnea directly from conversational speech, for example, in a telehealth application. We demonstrate with a collection of speech recordings before and after a light physical exercise that a siamese neural network, when presented examples of the two conditions, can detect the difference between two speech signals. This shows that this signal can be detected using data-pairs, removing the need for ratings of severity or the distinction of separate classes.

AB - Shortness of breath, or dyspnea is a condition of the cardiopulmonary system that may be caused by, for example, a heart or lung disease, or physical load. In this paper, we explore techniques of detecting mild dyspnea directly from conversational speech, for example, in a telehealth application. We demonstrate with a collection of speech recordings before and after a light physical exercise that a siamese neural network, when presented examples of the two conditions, can detect the difference between two speech signals. This shows that this signal can be detected using data-pairs, removing the need for ratings of severity or the distinction of separate classes.

KW - Data pairs

KW - Deeplearning

KW - Dyspnea

KW - Health monitoring

KW - Speech signal processing

UR - http://www.scopus.com/inward/record.url?scp=85091297925&partnerID=8YFLogxK

U2 - 10.1109/ICASSP40776.2020.9054751

DO - 10.1109/ICASSP40776.2020.9054751

M3 - Conference article in proceeding

AN - SCOPUS:85091297925

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 4102

EP - 4106

BT - 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings

PB - IEEE

T2 - 45th International Conference on Acoustics, Speech, and Signal Processing

Y2 - 4 May 2020 through 8 May 2020

ER -

Boelders S, Nallanthighal VS, Menkovski V, Härmä A. Detection of mild dyspnea from pairs of speech recordings. In 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings. IEEE. 2020. p. 4102-4106. 9054751. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Vol. 2020-May). doi: 10.1109/ICASSP40776.2020.9054751

Detection of mild dyspnea from pairs of speech recordings

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this