Validity of Off-the-Shelf Automatic Speech Recognition for Assessing Speech Intelligibility and Speech Severity in Speakers With Amyotrophic Lateral Sclerosis.

Purpose: There is increasing interest in using automatic speech recognition (ASR) systems to evaluate impairment severity or speech intelligibility in speakers with dysarthria. We assessed the clinical validity of one currently available off-the-shelf (OTS) ASR system (i.e., a Google Cloud ASR API)...

Descripción completa

Detalles Bibliográficos
Publicado en:Journal of Speech, Language & Hearing Research Vol. 65; no. 6; pp. 2128 - 2144
Autores principales: Gutz, Sarah E., Stipancic, Kaila L., Yunusova, Yana, Berry, James D., Green, Jordan R.
Formato: Artículo
Publicado: American Speech-Language-Hearing Association Jun2022
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=157403213&site=ehost-live
header:
  @attributes:
    shortDbName: ssf
    uiTerm: 157403213
    longDbName: Social Sciences Full Text (H.W. Wilson)
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        10924388
        1SM
      jtl: Journal of Speech, Language & Hearing Research
      issn: 10924388
      maglogo: N
    pubinfo:
      dt: Jun2022
      vid: 65
      iid: 6
      pid: 42
      pub: American Speech-Language-Hearing Association
    artinfo:
      ui:
        157403213
        10.1044/2022_JSLHR-21-00589
      ppf: 2128
      ppct: 16
      formats:
        fmt:
          @attributes:
            type: P
            size: 1.3MB
      tig:
        atl: Validity of Off-the-Shelf Automatic Speech Recognition for Assessing Speech Intelligibility and Speech Severity in Speakers With Amyotrophic Lateral Sclerosis.
      aug:
        au:
          Gutz, Sarah E.
          Stipancic, Kaila L.
          Yunusova, Yana
          Berry, James D.
          Green, Jordan R.
        affil:
          Program in Speech and Hearing Bioscience and Technology, Harvard Medical School, Boston, MA
          Department of Communicative Disorders and Sciences, University at Buffalo, NY
          Department of Speech-Language Pathology, University of Toronto, Ontario, Canada
          Hurvitz Brain Sciences Program, Sunnybrook Research Institute, Toronto, Ontario, Canada
          Toronto Rehabilitation Institute, University Health Network, Ontario, Canada
          Sean M. Healey and AMG Center for ALS, Massachusetts General Hospital, Boston
          Department of Communication Sciences and Disorders, MGH Institute of Health Professions, Boston, MA
      su:
        Judgment (Psychology)
        Automatic speech recognition
        Intelligibility of speech
        Amyotrophic lateral sclerosis
        Speech disorder diagnosis
        Speech evaluation
        Noise
        Quality assurance
      sug:
        subj:
          Judgment (Psychology)
          Automatic speech recognition
          Intelligibility of speech
          Amyotrophic lateral sclerosis
          Speech disorder diagnosis
          Speech evaluation
          Noise
          Quality assurance
      ab: Purpose: There is increasing interest in using automatic speech recognition (ASR) systems to evaluate impairment severity or speech intelligibility in speakers with dysarthria. We assessed the clinical validity of one currently available off-the-shelf (OTS) ASR system (i.e., a Google Cloud ASR API) for indexing sentence-level speech intelligibility and impairment severity in individuals with amyotrophic lateral sclerosis (ALS), and we provided guidance for potential users of such systems in research and clinic. Method: Using speech samples collected from 52 individuals with ALS and 20 healthy control speakers, we compared word recognition rate (WRR) from the commercially available Google Cloud ASR API (Machine WRR) to clinicianprovided judgments of impairment severity, as well as sentence intelligibility (Human WRR). We assessed the internal reliability of Machine and Human WRR by comparing the standard deviation of WRR across sentences to the minimally detectable change (MDC), a clinical benchmark that indicates whether results are within measurement error. We also evaluated Machine and Human WRR diagnostic accuracy for classifying speakers into clinically established categories. Results: Human WRR achieved better accuracy than Machine WRR when indexing speech severity, and, although related, Human and Machine WRR were not strongly correlated. When the speech signal was mixed with noise (noise-augmented ASR) to reduce a ceiling effect, Machine WRR performance improved. Internal reliability metrics were worse for Machine than Human WRR, particularly for typical and mildly impaired severity groups, although sentence length significantly impacted both Machine and Human WRRs. Conclusions: Results indicated that the OTS ASR system was inadequate for early detection of speech impairment and grading overall speech severity. While Machine and Human WRR were correlated, ASR should not be used as a one-toone proxy for transcription speech intelligibility or clinician severity ratings. Overall, findings suggested that the tested OTS ASR system, Google Cloud ASR, has limited utility for grading clinical speech impairment in speakers with ALS.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: N
    holdings:
      @attributes:
        islocal: N