EUVIMEDEUVIMED entdecken
Vergleichsstudie

Automated Speech Recognition in Adult Stroke Survivors: Comparing Human and Computer Transcriptions

Adam Jacks, Katarina L Haley, Gary Bishop, Tyson G Harmon

Folia Phoniatrica et Logopaedica · 2019 · 71 (5-6) · 286-296

DOI: 10.1159/000499156 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Folia Phoniatrica et Logopaedica, online erschienen am 22.05.2019. Verfasst von Adam Jacks und 3 weiteren Autor:innen. Beteiligte Einrichtung: Division of Speech and Hearing Sciences, Department of Allied Health Sciences, University of North Carolina at Chapel Hill, Chapel Hill, North Caroli…. Hauptthemen laut MEDLINE: Speech Recognition Software, Survivors. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: NIDCD NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Speech sound errors are common in people with a variety of communication disorders and can result in impaired message transmission to listeners. Valid and reliable metrics exist to quantify this problem, but they are rarely used in clinical settings due to the time-intensive nature of speech transcription by humans. Automated speech recognition (ASR) technologies have advanced substantially in recent years, enabling them to serve as realistic proxies for human listeners. This study aimed to determine how closely transcription scores from human listeners correspond to scores from an ASR system. Patients and Methods: Sentence recordings from 10 stroke survivors with aphasia and apraxia of speech were transcribed orthographically by 3 listeners and a web-based ASR service. Adjusted transcription scores were calculated for all samples based on accuracy of transcribed content words.

Results

As expected, transcription scores were significantly higher for the humans than for ASR. However, intraclass correlations revealed excellent agreement among the humans and ASR systems, and the systematically lower scores for computer speech recognition were effectively equalized simply by adding the regression intercept.

Conclusions

The results suggest the clinical feasibility of supplementing or substituting human transcriptions with computer-generated scores, though extension to other speech disorders requires further research.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Speech Recognition SoftwareSurvivorsAdultAgedAphasiaApraxiasFemaleHumansMaleMiddle AgedSpeech IntelligibilityStroke Rehabilitation

Stichwörter der Autor:innen

AphasiaAssessmentAutomated speech recognitionIntelligibilitySpeech transcriptionStroke

Autor:innen und Institutionen

  • Division of Speech and Hearing Sciences, Department of Allied Health Sciences, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA, adam_jacks@med.unc.edu.
  • Division of Speech and Hearing Sciences, Department of Allied Health Sciences, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA.
  • Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA.
  • Department of Communication Disorders, Brigham Young University, Provo, Utah, USA.

Förderung

  • NIDCD NIH HHS

Zitieren

APA

Jacks, A., Haley, K. L., Bishop, G., & Harmon, T. G. (2019). Automated Speech Recognition in Adult Stroke Survivors: Comparing Human and Computer Transcriptions. Folia Phoniatrica et Logopaedica, 71(5-6), 286-296. https://doi.org/10.1159/000499156

Vancouver

Jacks A, Haley KL, Bishop G, Harmon TG. Automated Speech Recognition in Adult Stroke Survivors: Comparing Human and Computer Transcriptions. Folia Phoniatrica et Logopaedica. 2019;71(5-6):286-296. doi:10.1159/000499156

BibTeX
@article{Jacks2019,
  author = {Jacks, Adam and Haley, Katarina L and Bishop, Gary and Harmon, Tyson G},
  title = {Automated Speech Recognition in Adult Stroke Survivors: Comparing Human and Computer Transcriptions},
  journal = {Folia Phoniatrica et Logopaedica},
  year = {2019},
  volume = {71},
  number = {5-6},
  pages = {286--296},
  doi = {10.1159/000499156}
}
Kostenlos starten →