PHONEME BASED RESPIRATORY ANALYSIS OF READ SPEECH

Venkata Srikanth Nallanthighal; Aki Härmä; Helmer Strik; Mathew Magimai Doss

doi:10.23919/EUSIPCO54536.2021.9615986

PHONEME BASED RESPIRATORY ANALYSIS OF READ SPEECH

Venkata Srikanth Nallanthighal
, Aki Härmä
, Helmer Strik
, Mathew Magimai Doss

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

Abstract

Recent work shows that it is possible to use deep learning techniques to sense the speaker's respiratory parameters directly from a speech signal. This can be a beneficial option for future telehealth services. In this paper, we dive deeper and study how respiratory effort depends on the linguistic content of the speech utterance. This is obtained by analysis of respiratory belt sensor data and phoneme-aligned speech data. The results show, for example, that the respiratory effort was highest for fricatives, compared to other broad phonetic classes, and especially high for the glottal consonants. The insights may help to develop more efficient protocols for respiratory health monitoring in telehealth applications.

Original language	English
Title of host publication	29th European Signal Processing Conference, EUSIPCO 2021 - Proceedings
Publisher	European Association for Signal Processing (EURASIP)
Pages	191-195
Number of pages	5
ISBN (Electronic)	9789082797060
DOIs	https://doi.org/10.23919/EUSIPCO54536.2021.9615986
Publication status	Published - 2021
Externally published	Yes
Event	29th European Signal Processing Conference - Dublin, Ireland Duration: 23 Aug 2021 → 27 Aug 2021 Conference number: 29

Publication series

Series	European Signal Processing Conference
Volume	2021-August
ISSN	2219-5491

Conference

Conference	29th European Signal Processing Conference
Abbreviated title	EUSIPCO 2021
Country/Territory	Ireland
City	Dublin
Period	23/08/21 → 27/08/21

Keywords

Breathing signal
Phonetics
Respiratory effort
Signal processing
Speech technology

Access to Document

10.23919/EUSIPCO54536.2021.9615986

Cite this

@inproceedings{34904bb032c9442fba658eba4be0aad5,

title = "PHONEME BASED RESPIRATORY ANALYSIS OF READ SPEECH",

abstract = "Recent work shows that it is possible to use deep learning techniques to sense the speaker's respiratory parameters directly from a speech signal. This can be a beneficial option for future telehealth services. In this paper, we dive deeper and study how respiratory effort depends on the linguistic content of the speech utterance. This is obtained by analysis of respiratory belt sensor data and phoneme-aligned speech data. The results show, for example, that the respiratory effort was highest for fricatives, compared to other broad phonetic classes, and especially high for the glottal consonants. The insights may help to develop more efficient protocols for respiratory health monitoring in telehealth applications.",

keywords = "Breathing signal, Phonetics, Respiratory effort, Signal processing, Speech technology",

author = "Nallanthighal, \{Venkata Srikanth\} and Aki H{\"a}rm{\"a} and Helmer Strik and Doss, \{Mathew Magimai\}",

note = "Funding Information: This work is supported under the EU's H2020 Marie Sk{\l}odowska-Curie programme TAPAS; Grant No: 766287. The authors would like to thank Qingran Zhan, IDIAP Research institute for the help with phoneme alignment. Funding Information: This work is supported under the EU{\textquoteright}s H2020 Marie Sk{\l}odowska-Curie programme TAPAS; Grant No: 766287. The authors would like to thank Qingran Zhan, IDIAP Research institute for the help with phoneme alignment. Publisher Copyright: {\textcopyright} 2021 European Signal Processing Conference. All rights reserved.; 29th European Signal Processing Conference, EUSIPCO 2021 ; Conference date: 23-08-2021 Through 27-08-2021",

year = "2021",

doi = "10.23919/EUSIPCO54536.2021.9615986",

language = "English",

series = "European Signal Processing Conference",

publisher = "European Association for Signal Processing (EURASIP)",

pages = "191--195",

booktitle = "29th European Signal Processing Conference, EUSIPCO 2021 - Proceedings",

address = "Belgium",

}

Nallanthighal, VS, Härmä, A, Strik, H & Doss, MM 2021, PHONEME BASED RESPIRATORY ANALYSIS OF READ SPEECH. in 29th European Signal Processing Conference, EUSIPCO 2021 - Proceedings. European Association for Signal Processing (EURASIP), European Signal Processing Conference, vol. 2021-August, pp. 191-195, 29th European Signal Processing Conference, Dublin, Ireland, 23/08/21. https://doi.org/10.23919/EUSIPCO54536.2021.9615986

PHONEME BASED RESPIRATORY ANALYSIS OF READ SPEECH. / Nallanthighal, Venkata Srikanth; Härmä, Aki; Strik, Helmer et al.
29th European Signal Processing Conference, EUSIPCO 2021 - Proceedings. European Association for Signal Processing (EURASIP), 2021. p. 191-195 (European Signal Processing Conference, Vol. 2021-August).

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

TY - GEN

T1 - PHONEME BASED RESPIRATORY ANALYSIS OF READ SPEECH

AU - Nallanthighal, Venkata Srikanth

AU - Härmä, Aki

AU - Strik, Helmer

AU - Doss, Mathew Magimai

N1 - Conference code: 29

PY - 2021

Y1 - 2021

N2 - Recent work shows that it is possible to use deep learning techniques to sense the speaker's respiratory parameters directly from a speech signal. This can be a beneficial option for future telehealth services. In this paper, we dive deeper and study how respiratory effort depends on the linguistic content of the speech utterance. This is obtained by analysis of respiratory belt sensor data and phoneme-aligned speech data. The results show, for example, that the respiratory effort was highest for fricatives, compared to other broad phonetic classes, and especially high for the glottal consonants. The insights may help to develop more efficient protocols for respiratory health monitoring in telehealth applications.

AB - Recent work shows that it is possible to use deep learning techniques to sense the speaker's respiratory parameters directly from a speech signal. This can be a beneficial option for future telehealth services. In this paper, we dive deeper and study how respiratory effort depends on the linguistic content of the speech utterance. This is obtained by analysis of respiratory belt sensor data and phoneme-aligned speech data. The results show, for example, that the respiratory effort was highest for fricatives, compared to other broad phonetic classes, and especially high for the glottal consonants. The insights may help to develop more efficient protocols for respiratory health monitoring in telehealth applications.

KW - Breathing signal

KW - Phonetics

KW - Respiratory effort

KW - Signal processing

KW - Speech technology

UR - https://www.scopus.com/pages/publications/85123207941

U2 - 10.23919/EUSIPCO54536.2021.9615986

DO - 10.23919/EUSIPCO54536.2021.9615986

M3 - Conference article in proceeding

AN - SCOPUS:85123207941

T3 - European Signal Processing Conference

SP - 191

EP - 195

BT - 29th European Signal Processing Conference, EUSIPCO 2021 - Proceedings

PB - European Association for Signal Processing (EURASIP)

T2 - 29th European Signal Processing Conference

Y2 - 23 August 2021 through 27 August 2021

ER -

PHONEME BASED RESPIRATORY ANALYSIS OF READ SPEECH

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this