Comprehension of synthetic speech and digitized natural speech by adults with aphasia

Karen Hux, Kelly Knollman-Porter, Jessica Brown, Sarah E. Wallace

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Using text-to-speech technology to provide simultaneous written and auditory content presentation may help compensate for chronic reading challenges if people with aphasia can understand synthetic speech output; however, inherent auditory comprehension challenges experienced by people with aphasia may make understanding synthetic speech difficult. This study's purpose was to compare the preferences and auditory comprehension accuracy of people with aphasia when listening to sentences generated with digitized natural speech, Alex synthetic speech (i.e., Macintosh platform), or David synthetic speech (i.e., Windows platform). The methodology required each of 20 participants with aphasia to select one of four images corresponding in meaning to each of 60 sentences comprising three stimulus sets. Results revealed significantly better accuracy given digitized natural speech than either synthetic speech option; however, individual participant performance analyses revealed three patterns: (a) comparable accuracy regardless of speech condition for 30% of participants, (b) comparable accuracy between digitized natural speech and one, but not both, synthetic speech option for 45% of participants, and (c) greater accuracy with digitized natural speech than with either synthetic speech option for remaining participants. Ranking and Likert-scale rating data revealed a preference for digitized natural speech and David synthetic speech over Alex synthetic speech. Results suggest many individuals with aphasia can comprehend synthetic speech options available on popular operating systems. Further examination of synthetic speech use to support reading comprehension through text-to-speech technology is thus warranted.

Original languageEnglish (US)
Pages (from-to)15-26
Number of pages12
JournalJournal of Communication Disorders
Volume69
DOIs
StatePublished - Sep 2017

Fingerprint

Aphasia
speech disorder
comprehension
Reading
Technology

Keywords

  • Aphasia
  • Auditory comprehension
  • Computer-generated speech
  • Synthetic speech

ASJC Scopus subject areas

  • Experimental and Cognitive Psychology
  • Linguistics and Language
  • Cognitive Neuroscience
  • Speech and Hearing
  • LPN and LVN

Cite this

Comprehension of synthetic speech and digitized natural speech by adults with aphasia. / Hux, Karen; Knollman-Porter, Kelly; Brown, Jessica; Wallace, Sarah E.

In: Journal of Communication Disorders, Vol. 69, 09.2017, p. 15-26.

Research output: Contribution to journalArticle

Hux, Karen ; Knollman-Porter, Kelly ; Brown, Jessica ; Wallace, Sarah E. / Comprehension of synthetic speech and digitized natural speech by adults with aphasia. In: Journal of Communication Disorders. 2017 ; Vol. 69. pp. 15-26.
@article{40f65c64c2e540939f61ae077d5855b7,
title = "Comprehension of synthetic speech and digitized natural speech by adults with aphasia",
abstract = "Using text-to-speech technology to provide simultaneous written and auditory content presentation may help compensate for chronic reading challenges if people with aphasia can understand synthetic speech output; however, inherent auditory comprehension challenges experienced by people with aphasia may make understanding synthetic speech difficult. This study's purpose was to compare the preferences and auditory comprehension accuracy of people with aphasia when listening to sentences generated with digitized natural speech, Alex synthetic speech (i.e., Macintosh platform), or David synthetic speech (i.e., Windows platform). The methodology required each of 20 participants with aphasia to select one of four images corresponding in meaning to each of 60 sentences comprising three stimulus sets. Results revealed significantly better accuracy given digitized natural speech than either synthetic speech option; however, individual participant performance analyses revealed three patterns: (a) comparable accuracy regardless of speech condition for 30{\%} of participants, (b) comparable accuracy between digitized natural speech and one, but not both, synthetic speech option for 45{\%} of participants, and (c) greater accuracy with digitized natural speech than with either synthetic speech option for remaining participants. Ranking and Likert-scale rating data revealed a preference for digitized natural speech and David synthetic speech over Alex synthetic speech. Results suggest many individuals with aphasia can comprehend synthetic speech options available on popular operating systems. Further examination of synthetic speech use to support reading comprehension through text-to-speech technology is thus warranted.",
keywords = "Aphasia, Auditory comprehension, Computer-generated speech, Synthetic speech",
author = "Karen Hux and Kelly Knollman-Porter and Jessica Brown and Wallace, {Sarah E.}",
year = "2017",
month = "9",
doi = "10.1016/j.jcomdis.2017.06.006",
language = "English (US)",
volume = "69",
pages = "15--26",
journal = "Journal of Communication Disorders",
issn = "0021-9924",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Comprehension of synthetic speech and digitized natural speech by adults with aphasia

AU - Hux, Karen

AU - Knollman-Porter, Kelly

AU - Brown, Jessica

AU - Wallace, Sarah E.

PY - 2017/9

Y1 - 2017/9

N2 - Using text-to-speech technology to provide simultaneous written and auditory content presentation may help compensate for chronic reading challenges if people with aphasia can understand synthetic speech output; however, inherent auditory comprehension challenges experienced by people with aphasia may make understanding synthetic speech difficult. This study's purpose was to compare the preferences and auditory comprehension accuracy of people with aphasia when listening to sentences generated with digitized natural speech, Alex synthetic speech (i.e., Macintosh platform), or David synthetic speech (i.e., Windows platform). The methodology required each of 20 participants with aphasia to select one of four images corresponding in meaning to each of 60 sentences comprising three stimulus sets. Results revealed significantly better accuracy given digitized natural speech than either synthetic speech option; however, individual participant performance analyses revealed three patterns: (a) comparable accuracy regardless of speech condition for 30% of participants, (b) comparable accuracy between digitized natural speech and one, but not both, synthetic speech option for 45% of participants, and (c) greater accuracy with digitized natural speech than with either synthetic speech option for remaining participants. Ranking and Likert-scale rating data revealed a preference for digitized natural speech and David synthetic speech over Alex synthetic speech. Results suggest many individuals with aphasia can comprehend synthetic speech options available on popular operating systems. Further examination of synthetic speech use to support reading comprehension through text-to-speech technology is thus warranted.

AB - Using text-to-speech technology to provide simultaneous written and auditory content presentation may help compensate for chronic reading challenges if people with aphasia can understand synthetic speech output; however, inherent auditory comprehension challenges experienced by people with aphasia may make understanding synthetic speech difficult. This study's purpose was to compare the preferences and auditory comprehension accuracy of people with aphasia when listening to sentences generated with digitized natural speech, Alex synthetic speech (i.e., Macintosh platform), or David synthetic speech (i.e., Windows platform). The methodology required each of 20 participants with aphasia to select one of four images corresponding in meaning to each of 60 sentences comprising three stimulus sets. Results revealed significantly better accuracy given digitized natural speech than either synthetic speech option; however, individual participant performance analyses revealed three patterns: (a) comparable accuracy regardless of speech condition for 30% of participants, (b) comparable accuracy between digitized natural speech and one, but not both, synthetic speech option for 45% of participants, and (c) greater accuracy with digitized natural speech than with either synthetic speech option for remaining participants. Ranking and Likert-scale rating data revealed a preference for digitized natural speech and David synthetic speech over Alex synthetic speech. Results suggest many individuals with aphasia can comprehend synthetic speech options available on popular operating systems. Further examination of synthetic speech use to support reading comprehension through text-to-speech technology is thus warranted.

KW - Aphasia

KW - Auditory comprehension

KW - Computer-generated speech

KW - Synthetic speech

UR - http://www.scopus.com/inward/record.url?scp=85022034418&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85022034418&partnerID=8YFLogxK

U2 - 10.1016/j.jcomdis.2017.06.006

DO - 10.1016/j.jcomdis.2017.06.006

M3 - Article

C2 - 28704689

AN - SCOPUS:85022034418

VL - 69

SP - 15

EP - 26

JO - Journal of Communication Disorders

JF - Journal of Communication Disorders

SN - 0021-9924

ER -