Evaluation of a speech recognition prototype for speakers with moderate and severe dysarthria: A preliminary report

Susan K. Fager, David R. Beukelman, Tom Jakobs, John Paul Hosom

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

This study described preliminary work with the Supplemented Speech Recognition (SSR) system for speakers with dysarthria. SSR incorporated automatic speech recognition optimized for dysarthric speech, alphabet supplementation, and word prediction. Participants included seven individuals with a range of dysarthria severity. Keystroke savings using SSR averaged 68.2% for typical sentences and 67.5% for atypical phrases. This was significantly different to using word prediction alone. The SSR correctly identified an average of 80.7% of target stimulus words for typical sentences and 82.8% for atypical phrases. Statistical significance could not be claimed for the relations between sentence intelligibility and keystroke savings or sentence intelligibility and system performance. The results suggest that individuals with dysarthria using SSR could achieve comparable keystroke savings regardless of speech severity.

Original languageEnglish (US)
Pages (from-to)267-277
Number of pages11
JournalAAC: Augmentative and Alternative Communication
Volume26
Issue number4
DOIs
StatePublished - Dec 1 2010

Fingerprint

Dysarthria

Keywords

  • Dysarthria
  • Speech recognition
  • Supplemented speech
  • Voice recognition

ASJC Scopus subject areas

  • Rehabilitation
  • Speech and Hearing

Cite this

Evaluation of a speech recognition prototype for speakers with moderate and severe dysarthria : A preliminary report. / Fager, Susan K.; Beukelman, David R.; Jakobs, Tom; Hosom, John Paul.

In: AAC: Augmentative and Alternative Communication, Vol. 26, No. 4, 01.12.2010, p. 267-277.

Research output: Contribution to journalArticle

Fager, Susan K. ; Beukelman, David R. ; Jakobs, Tom ; Hosom, John Paul. / Evaluation of a speech recognition prototype for speakers with moderate and severe dysarthria : A preliminary report. In: AAC: Augmentative and Alternative Communication. 2010 ; Vol. 26, No. 4. pp. 267-277.
@article{d73c07fbdff74f0ba3aa11d8d93103fc,
title = "Evaluation of a speech recognition prototype for speakers with moderate and severe dysarthria: A preliminary report",
abstract = "This study described preliminary work with the Supplemented Speech Recognition (SSR) system for speakers with dysarthria. SSR incorporated automatic speech recognition optimized for dysarthric speech, alphabet supplementation, and word prediction. Participants included seven individuals with a range of dysarthria severity. Keystroke savings using SSR averaged 68.2{\%} for typical sentences and 67.5{\%} for atypical phrases. This was significantly different to using word prediction alone. The SSR correctly identified an average of 80.7{\%} of target stimulus words for typical sentences and 82.8{\%} for atypical phrases. Statistical significance could not be claimed for the relations between sentence intelligibility and keystroke savings or sentence intelligibility and system performance. The results suggest that individuals with dysarthria using SSR could achieve comparable keystroke savings regardless of speech severity.",
keywords = "Dysarthria, Speech recognition, Supplemented speech, Voice recognition",
author = "Fager, {Susan K.} and Beukelman, {David R.} and Tom Jakobs and Hosom, {John Paul}",
year = "2010",
month = "12",
day = "1",
doi = "10.3109/07434618.2010.532508",
language = "English (US)",
volume = "26",
pages = "267--277",
journal = "AAC: Augmentative and Alternative Communication",
issn = "0743-4618",
publisher = "Informa Healthcare",
number = "4",

}

TY - JOUR

T1 - Evaluation of a speech recognition prototype for speakers with moderate and severe dysarthria

T2 - A preliminary report

AU - Fager, Susan K.

AU - Beukelman, David R.

AU - Jakobs, Tom

AU - Hosom, John Paul

PY - 2010/12/1

Y1 - 2010/12/1

N2 - This study described preliminary work with the Supplemented Speech Recognition (SSR) system for speakers with dysarthria. SSR incorporated automatic speech recognition optimized for dysarthric speech, alphabet supplementation, and word prediction. Participants included seven individuals with a range of dysarthria severity. Keystroke savings using SSR averaged 68.2% for typical sentences and 67.5% for atypical phrases. This was significantly different to using word prediction alone. The SSR correctly identified an average of 80.7% of target stimulus words for typical sentences and 82.8% for atypical phrases. Statistical significance could not be claimed for the relations between sentence intelligibility and keystroke savings or sentence intelligibility and system performance. The results suggest that individuals with dysarthria using SSR could achieve comparable keystroke savings regardless of speech severity.

AB - This study described preliminary work with the Supplemented Speech Recognition (SSR) system for speakers with dysarthria. SSR incorporated automatic speech recognition optimized for dysarthric speech, alphabet supplementation, and word prediction. Participants included seven individuals with a range of dysarthria severity. Keystroke savings using SSR averaged 68.2% for typical sentences and 67.5% for atypical phrases. This was significantly different to using word prediction alone. The SSR correctly identified an average of 80.7% of target stimulus words for typical sentences and 82.8% for atypical phrases. Statistical significance could not be claimed for the relations between sentence intelligibility and keystroke savings or sentence intelligibility and system performance. The results suggest that individuals with dysarthria using SSR could achieve comparable keystroke savings regardless of speech severity.

KW - Dysarthria

KW - Speech recognition

KW - Supplemented speech

KW - Voice recognition

UR - http://www.scopus.com/inward/record.url?scp=78649347622&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649347622&partnerID=8YFLogxK

U2 - 10.3109/07434618.2010.532508

DO - 10.3109/07434618.2010.532508

M3 - Article

C2 - 21091303

AN - SCOPUS:78649347622

VL - 26

SP - 267

EP - 277

JO - AAC: Augmentative and Alternative Communication

JF - AAC: Augmentative and Alternative Communication

SN - 0743-4618

IS - 4

ER -