Predicting intelligibility gains in dysarthria through automated speech feature analysis

Annalise R. Fletcher, Alan A. Wisler, Megan J. McAuliffe, Kaitlin L. Lansford, Julie Liss

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Purpose: Behavioral speech modifications have variable effects on the intelligibility of speakers with dysarthria. In the companion article, a significant relationship was found between measures of speakers’ baseline speech and their intelligibility gains following cues to speak louder and reduce rate (Fletcher, McAuliffe, Lansford, Sinex, & Liss, 2017). This study reexamines these features and assesses whether automated acoustic assessments can also be used to predict intelligibility gains. Method: Fifty speakers (7 older individuals and 43 with dysarthria) read a passage in habitual, loud, and slow speaking modes. Automated measurements of long-term average spectra, envelope modulation spectra, and Mel-frequency cepstral coefficients were extracted from short segments of participants’ baseline speech. Intelligibility gains were statistically modeled, and the predictive power of the baseline speech measures was assessed using cross-validation. Results: Statistical models could predict the intelligibility gains of speakers they had not been trained on. The automated acoustic features were better able to predict speakers’ improvement in the loud condition than the manual measures reported in the companion article. Conclusions: These acoustic analyses present a promising tool for rapidly assessing treatment options. Automated measures of baseline speech patterns may enable more selective inclusion criteria and stronger group outcomes within treatment studies.

Original languageEnglish (US)
Pages (from-to)3058-3068
Number of pages11
JournalJournal of Speech, Language, and Hearing Research
Volume60
Issue number11
DOIs
StatePublished - Nov 1 2017

Fingerprint

Dysarthria
Acoustics
acoustics
Speech Intelligibility
Statistical Models
Cues
speaking
inclusion
Intelligibility
Group

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language
  • Speech and Hearing

Cite this

Predicting intelligibility gains in dysarthria through automated speech feature analysis. / Fletcher, Annalise R.; Wisler, Alan A.; McAuliffe, Megan J.; Lansford, Kaitlin L.; Liss, Julie.

In: Journal of Speech, Language, and Hearing Research, Vol. 60, No. 11, 01.11.2017, p. 3058-3068.

Research output: Contribution to journalArticle

Fletcher, Annalise R. ; Wisler, Alan A. ; McAuliffe, Megan J. ; Lansford, Kaitlin L. ; Liss, Julie. / Predicting intelligibility gains in dysarthria through automated speech feature analysis. In: Journal of Speech, Language, and Hearing Research. 2017 ; Vol. 60, No. 11. pp. 3058-3068.
@article{11c7d10d67da495aaac03adb63c963db,
title = "Predicting intelligibility gains in dysarthria through automated speech feature analysis",
abstract = "Purpose: Behavioral speech modifications have variable effects on the intelligibility of speakers with dysarthria. In the companion article, a significant relationship was found between measures of speakers’ baseline speech and their intelligibility gains following cues to speak louder and reduce rate (Fletcher, McAuliffe, Lansford, Sinex, & Liss, 2017). This study reexamines these features and assesses whether automated acoustic assessments can also be used to predict intelligibility gains. Method: Fifty speakers (7 older individuals and 43 with dysarthria) read a passage in habitual, loud, and slow speaking modes. Automated measurements of long-term average spectra, envelope modulation spectra, and Mel-frequency cepstral coefficients were extracted from short segments of participants’ baseline speech. Intelligibility gains were statistically modeled, and the predictive power of the baseline speech measures was assessed using cross-validation. Results: Statistical models could predict the intelligibility gains of speakers they had not been trained on. The automated acoustic features were better able to predict speakers’ improvement in the loud condition than the manual measures reported in the companion article. Conclusions: These acoustic analyses present a promising tool for rapidly assessing treatment options. Automated measures of baseline speech patterns may enable more selective inclusion criteria and stronger group outcomes within treatment studies.",
author = "Fletcher, {Annalise R.} and Wisler, {Alan A.} and McAuliffe, {Megan J.} and Lansford, {Kaitlin L.} and Julie Liss",
year = "2017",
month = "11",
day = "1",
doi = "10.1044/2017_JSLHR-S-16-0453",
language = "English (US)",
volume = "60",
pages = "3058--3068",
journal = "Journal of Speech, Language, and Hearing Research",
issn = "1092-4388",
publisher = "American Speech-Language-Hearing Association (ASHA)",
number = "11",

}

TY - JOUR

T1 - Predicting intelligibility gains in dysarthria through automated speech feature analysis

AU - Fletcher, Annalise R.

AU - Wisler, Alan A.

AU - McAuliffe, Megan J.

AU - Lansford, Kaitlin L.

AU - Liss, Julie

PY - 2017/11/1

Y1 - 2017/11/1

N2 - Purpose: Behavioral speech modifications have variable effects on the intelligibility of speakers with dysarthria. In the companion article, a significant relationship was found between measures of speakers’ baseline speech and their intelligibility gains following cues to speak louder and reduce rate (Fletcher, McAuliffe, Lansford, Sinex, & Liss, 2017). This study reexamines these features and assesses whether automated acoustic assessments can also be used to predict intelligibility gains. Method: Fifty speakers (7 older individuals and 43 with dysarthria) read a passage in habitual, loud, and slow speaking modes. Automated measurements of long-term average spectra, envelope modulation spectra, and Mel-frequency cepstral coefficients were extracted from short segments of participants’ baseline speech. Intelligibility gains were statistically modeled, and the predictive power of the baseline speech measures was assessed using cross-validation. Results: Statistical models could predict the intelligibility gains of speakers they had not been trained on. The automated acoustic features were better able to predict speakers’ improvement in the loud condition than the manual measures reported in the companion article. Conclusions: These acoustic analyses present a promising tool for rapidly assessing treatment options. Automated measures of baseline speech patterns may enable more selective inclusion criteria and stronger group outcomes within treatment studies.

AB - Purpose: Behavioral speech modifications have variable effects on the intelligibility of speakers with dysarthria. In the companion article, a significant relationship was found between measures of speakers’ baseline speech and their intelligibility gains following cues to speak louder and reduce rate (Fletcher, McAuliffe, Lansford, Sinex, & Liss, 2017). This study reexamines these features and assesses whether automated acoustic assessments can also be used to predict intelligibility gains. Method: Fifty speakers (7 older individuals and 43 with dysarthria) read a passage in habitual, loud, and slow speaking modes. Automated measurements of long-term average spectra, envelope modulation spectra, and Mel-frequency cepstral coefficients were extracted from short segments of participants’ baseline speech. Intelligibility gains were statistically modeled, and the predictive power of the baseline speech measures was assessed using cross-validation. Results: Statistical models could predict the intelligibility gains of speakers they had not been trained on. The automated acoustic features were better able to predict speakers’ improvement in the loud condition than the manual measures reported in the companion article. Conclusions: These acoustic analyses present a promising tool for rapidly assessing treatment options. Automated measures of baseline speech patterns may enable more selective inclusion criteria and stronger group outcomes within treatment studies.

UR - http://www.scopus.com/inward/record.url?scp=85033710204&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85033710204&partnerID=8YFLogxK

U2 - 10.1044/2017_JSLHR-S-16-0453

DO - 10.1044/2017_JSLHR-S-16-0453

M3 - Article

C2 - 29075755

AN - SCOPUS:85033710204

VL - 60

SP - 3058

EP - 3068

JO - Journal of Speech, Language, and Hearing Research

JF - Journal of Speech, Language, and Hearing Research

SN - 1092-4388

IS - 11

ER -