Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Voice fatigue subtyping through individual modeling of vocal demand reponses

Berardi, Mark L. ; Whitling, Susanna LU and Hunter, Eric J. (2025) In Scientific Reports 15(1).
Abstract

Recognizing individual variability is essential for developing targeted, personalized medical interventions. Vocal fatigue is a prevalent symptom and complaint among occupational voice users, but its identification has yielded mixed results. Vocal fatigue is a complex issue with heterogeneous biophysiological responses to vocal demands among individuals. This research aims to classify individuals as vocal demand responders to measure changes in vocal performance consistent with state vocal fatigue. A total of 37 participants (19F, 18M) completed a 30-minute vocal loading task (VLT) which consisted of loud speaking with background noise. Participants provided speech samples pre- and post-VLT and rated their vocal effort levels before,... (More)

Recognizing individual variability is essential for developing targeted, personalized medical interventions. Vocal fatigue is a prevalent symptom and complaint among occupational voice users, but its identification has yielded mixed results. Vocal fatigue is a complex issue with heterogeneous biophysiological responses to vocal demands among individuals. This research aims to classify individuals as vocal demand responders to measure changes in vocal performance consistent with state vocal fatigue. A total of 37 participants (19F, 18M) completed a 30-minute vocal loading task (VLT) which consisted of loud speaking with background noise. Participants provided speech samples pre- and post-VLT and rated their vocal effort levels before, every 5 minutes during, and after the VLT. Perceived effort ratings and measured vocal performance from the speech samples were used to classify participants into distinct subgroups of vocal demand responders. Prior to classification there were few detectable changes associated with the VLT. However, the subgroup with both vocal effort and voice production demand responses displayed significant changes consistent with vocal fatigue while the other subgroups did not. These findings support the need for an individual-based approach to subtyping and measuring vocal fatigue and highlight its heterogeneous nature.

(Less)
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Machine learning, Precision medicine, Vocal fatigue, Vocal loading task, Voice production
in
Scientific Reports
volume
15
issue
1
article number
25718
publisher
Nature Publishing Group
external identifiers
  • pmid:40670511
  • scopus:105010746893
ISSN
2045-2322
DOI
10.1038/s41598-025-10565-2
language
English
LU publication?
yes
id
a8102ac1-04d6-4c7f-9e13-3a5cb2965a98
date added to LUP
2025-10-22 14:41:34
date last changed
2025-10-23 03:00:05
@article{a8102ac1-04d6-4c7f-9e13-3a5cb2965a98,
  abstract     = {{<p>Recognizing individual variability is essential for developing targeted, personalized medical interventions. Vocal fatigue is a prevalent symptom and complaint among occupational voice users, but its identification has yielded mixed results. Vocal fatigue is a complex issue with heterogeneous biophysiological responses to vocal demands among individuals. This research aims to classify individuals as vocal demand responders to measure changes in vocal performance consistent with state vocal fatigue. A total of 37 participants (19F, 18M) completed a 30-minute vocal loading task (VLT) which consisted of loud speaking with background noise. Participants provided speech samples pre- and post-VLT and rated their vocal effort levels before, every 5 minutes during, and after the VLT. Perceived effort ratings and measured vocal performance from the speech samples were used to classify participants into distinct subgroups of vocal demand responders. Prior to classification there were few detectable changes associated with the VLT. However, the subgroup with both vocal effort and voice production demand responses displayed significant changes consistent with vocal fatigue while the other subgroups did not. These findings support the need for an individual-based approach to subtyping and measuring vocal fatigue and highlight its heterogeneous nature.</p>}},
  author       = {{Berardi, Mark L. and Whitling, Susanna and Hunter, Eric J.}},
  issn         = {{2045-2322}},
  keywords     = {{Machine learning; Precision medicine; Vocal fatigue; Vocal loading task; Voice production}},
  language     = {{eng}},
  number       = {{1}},
  publisher    = {{Nature Publishing Group}},
  series       = {{Scientific Reports}},
  title        = {{Voice fatigue subtyping through individual modeling of vocal demand reponses}},
  url          = {{http://dx.doi.org/10.1038/s41598-025-10565-2}},
  doi          = {{10.1038/s41598-025-10565-2}},
  volume       = {{15}},
  year         = {{2025}},
}