DEVELOPING A MACHINE-LEARNING MODEL FOR DETECTING INTELLIGIBILITY DIFFERENCES IN INDIVIDUALS WITH VOICE DISORDERS: A FEASIBILITY STUDY

Mary Pietrowicz; Diana Orbelo; Amrit Kamboj; Manoj Krishna Yarlagadda; Kevin Buller; Sara Charney; Cadman Leggett; Keiko Ishikawa

DEVELOPING A MACHINE-LEARNING MODEL FOR DETECTING INTELLIGIBILITY DIFFERENCES IN INDIVIDUALS WITH VOICE DISORDERS: A FEASIBILITY STUDY

Mary Pietrowicz, Diana Orbelo, Amrit Kamboj, Manoj Krishna Yarlagadda, Kevin Buller, Sara Charney, Cadman Leggett, Keiko Ishikawa

Communication Sciences and Disorders

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

Abstract

Voice disorders can reduce an individual's ability to produce intelligible speech; however, intelligibility in dysphonia has limited study. Current methods of intelligibility assessment are subjective and time-consuming, making reliable, efficient monitoring of patient progress difficult for clinicians. Machine-learning techniques, however, may provide novel, automated assessment solutions. This study aims to discover machine-learning models that differentiate habitual speech (HS) from hyperarticulated or “clear speech” (CS). Two corpora with same-subject recordings of HS and CS were used. The corpus consisted of 115 speakers, 65 healthy and 50 with mild-to-moderate voice disorders, saying six sentences from the Consensus of Auditory-Perceptual Evaluation. Acoustic analyses revealed significant differences between HS and CS in speech rate and CPP for female speakers. Various machine modeling techniques are explored for their ability to differentiate HS and CS, and the results are reported.

Original language	English
Title of host publication	Forum Acusticum 2023 - 10th Convention of the European Acoustics Association, EAA 2023
ISBN (Electronic)	9788888942674
State	Published - 2023
Event	10th Convention of the European Acoustics Association, EAA 2023 - Torino, Italy Duration: Sep 11 2023 → Sep 15 2023

Publication series

Name	Proceedings of Forum Acusticum
ISSN (Print)	2221-3767

Conference

Conference	10th Convention of the European Acoustics Association, EAA 2023
Country/Territory	Italy
City	Torino
Period	9/11/23 → 9/15/23

Bibliographical note

Publisher Copyright:
© 2023 First author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 Unported License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Funding

This work was funded in part by Mayo Clinic's Departments of Otolaryngology (PI: Orbelo) and Gastroenterology (PI: Leggett) Small Grant Programs and a Mayo Max Innovation Award (PI: Leggett).

Funders	Funder number
Mayo Clinic Rochester
Mayo Max Innovation

Keywords

AI
clear speech
intelligibility
machine learning
voice disorders

ASJC Scopus subject areas

Acoustics and Ultrasonics

Cite this

Pietrowicz, M., Orbelo, D., Kamboj, A., Yarlagadda, M. K., Buller, K., Charney, S., Leggett, C., & Ishikawa, K. (2023). DEVELOPING A MACHINE-LEARNING MODEL FOR DETECTING INTELLIGIBILITY DIFFERENCES IN INDIVIDUALS WITH VOICE DISORDERS: A FEASIBILITY STUDY. In Forum Acusticum 2023 - 10th Convention of the European Acoustics Association, EAA 2023 (Proceedings of Forum Acusticum).

@inproceedings{c58aa4b7775444c18b0dd71aa2c086f9,

title = "DEVELOPING A MACHINE-LEARNING MODEL FOR DETECTING INTELLIGIBILITY DIFFERENCES IN INDIVIDUALS WITH VOICE DISORDERS: A FEASIBILITY STUDY",

abstract = "Voice disorders can reduce an individual's ability to produce intelligible speech; however, intelligibility in dysphonia has limited study. Current methods of intelligibility assessment are subjective and time-consuming, making reliable, efficient monitoring of patient progress difficult for clinicians. Machine-learning techniques, however, may provide novel, automated assessment solutions. This study aims to discover machine-learning models that differentiate habitual speech (HS) from hyperarticulated or “clear speech” (CS). Two corpora with same-subject recordings of HS and CS were used. The corpus consisted of 115 speakers, 65 healthy and 50 with mild-to-moderate voice disorders, saying six sentences from the Consensus of Auditory-Perceptual Evaluation. Acoustic analyses revealed significant differences between HS and CS in speech rate and CPP for female speakers. Various machine modeling techniques are explored for their ability to differentiate HS and CS, and the results are reported.",

keywords = "AI, clear speech, intelligibility, machine learning, voice disorders",

author = "Mary Pietrowicz and Diana Orbelo and Amrit Kamboj and Yarlagadda, {Manoj Krishna} and Kevin Buller and Sara Charney and Cadman Leggett and Keiko Ishikawa",

note = "Publisher Copyright: {\textcopyright} 2023 First author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 Unported License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.; 10th Convention of the European Acoustics Association, EAA 2023 ; Conference date: 11-09-2023 Through 15-09-2023",

year = "2023",

language = "English",

series = "Proceedings of Forum Acusticum",

booktitle = "Forum Acusticum 2023 - 10th Convention of the European Acoustics Association, EAA 2023",

}

Pietrowicz, M, Orbelo, D, Kamboj, A, Yarlagadda, MK, Buller, K, Charney, S, Leggett, C & Ishikawa, K 2023, DEVELOPING A MACHINE-LEARNING MODEL FOR DETECTING INTELLIGIBILITY DIFFERENCES IN INDIVIDUALS WITH VOICE DISORDERS: A FEASIBILITY STUDY. in Forum Acusticum 2023 - 10th Convention of the European Acoustics Association, EAA 2023. Proceedings of Forum Acusticum, 10th Convention of the European Acoustics Association, EAA 2023, Torino, Italy, 9/11/23.

DEVELOPING A MACHINE-LEARNING MODEL FOR DETECTING INTELLIGIBILITY DIFFERENCES IN INDIVIDUALS WITH VOICE DISORDERS: A FEASIBILITY STUDY. / Pietrowicz, Mary; Orbelo, Diana; Kamboj, Amrit et al.
Forum Acusticum 2023 - 10th Convention of the European Acoustics Association, EAA 2023. 2023. (Proceedings of Forum Acusticum).

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

TY - GEN

T1 - DEVELOPING A MACHINE-LEARNING MODEL FOR DETECTING INTELLIGIBILITY DIFFERENCES IN INDIVIDUALS WITH VOICE DISORDERS

T2 - 10th Convention of the European Acoustics Association, EAA 2023

AU - Pietrowicz, Mary

AU - Orbelo, Diana

AU - Kamboj, Amrit

AU - Yarlagadda, Manoj Krishna

AU - Buller, Kevin

AU - Charney, Sara

AU - Leggett, Cadman

AU - Ishikawa, Keiko

N1 - Publisher Copyright: © 2023 First author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 Unported License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

PY - 2023

Y1 - 2023

N2 - Voice disorders can reduce an individual's ability to produce intelligible speech; however, intelligibility in dysphonia has limited study. Current methods of intelligibility assessment are subjective and time-consuming, making reliable, efficient monitoring of patient progress difficult for clinicians. Machine-learning techniques, however, may provide novel, automated assessment solutions. This study aims to discover machine-learning models that differentiate habitual speech (HS) from hyperarticulated or “clear speech” (CS). Two corpora with same-subject recordings of HS and CS were used. The corpus consisted of 115 speakers, 65 healthy and 50 with mild-to-moderate voice disorders, saying six sentences from the Consensus of Auditory-Perceptual Evaluation. Acoustic analyses revealed significant differences between HS and CS in speech rate and CPP for female speakers. Various machine modeling techniques are explored for their ability to differentiate HS and CS, and the results are reported.

AB - Voice disorders can reduce an individual's ability to produce intelligible speech; however, intelligibility in dysphonia has limited study. Current methods of intelligibility assessment are subjective and time-consuming, making reliable, efficient monitoring of patient progress difficult for clinicians. Machine-learning techniques, however, may provide novel, automated assessment solutions. This study aims to discover machine-learning models that differentiate habitual speech (HS) from hyperarticulated or “clear speech” (CS). Two corpora with same-subject recordings of HS and CS were used. The corpus consisted of 115 speakers, 65 healthy and 50 with mild-to-moderate voice disorders, saying six sentences from the Consensus of Auditory-Perceptual Evaluation. Acoustic analyses revealed significant differences between HS and CS in speech rate and CPP for female speakers. Various machine modeling techniques are explored for their ability to differentiate HS and CS, and the results are reported.

KW - AI

KW - clear speech

KW - intelligibility

KW - machine learning

KW - voice disorders

UR - http://www.scopus.com/inward/record.url?scp=85191254242&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85191254242&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85191254242

T3 - Proceedings of Forum Acusticum

BT - Forum Acusticum 2023 - 10th Convention of the European Acoustics Association, EAA 2023

Y2 - 11 September 2023 through 15 September 2023

ER -

DEVELOPING A MACHINE-LEARNING MODEL FOR DETECTING INTELLIGIBILITY DIFFERENCES IN INDIVIDUALS WITH VOICE DISORDERS: A FEASIBILITY STUDY

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this