View in EDS PDF Full Text

Community-Supported Shared Infrastructure in Support of Speech Accessibility.

Saved in:
Bibliographic Details
Title: Community-Supported Shared Infrastructure in Support of Speech Accessibility.
Authors: Hasegawa-Johnson, Mark1 jhasegaw@illinois.edu, Xiuwen Zheng1, Heejin Kim1, Mendes, Clarion1, Dickinson, Meg1, Hege, Erik1, Zwilling, Chris1, Moore Channell, Marie1, Mattie, Laura1, Hodges, Heather2, Ramig, Lorraine2, Bellard, Mary3, Shebanek, Mike4, Sari, Leda4, Kalgaonkar, Kaustubh4, Frerichs, David5, Bigham, Jeffrey P.6, Findlater, Leah6, Lea, Colin6, Herrlinger, Sarah6
Source: Journal of Speech, Language & Hearing Research. Nov2024, Vol. 67 Issue 11, p4162-4175. 14p.
Subject Terms: *Community support, *Health services accessibility, *Dysarthria, *Assistive technology, *Speech disorders, *Machine learning, *People with disabilities, Automatic speech recognition, Cell phones, Descriptive statistics, Parkinson's disease, Personal computers, Data analysis software
Geographic Terms: Illinois, United States
Abstract: Purpose: The Speech Accessibility Project (SAP) intends to facilitate research and development in automatic speech recognition (ASR) and other machine learning tasks for people with speech disabilities. The purpose of this article is to introduce this project as a resource for researchers, including baseline analysis of the first released data package. Method: The project aims to facilitate ASR research by collecting, curating, and distributing transcribed U.S. English speech from people with speech and/or language disabilities. Participants record speech from their place of residence by connecting their personal computer, cell phone, and assistive devices, if needed, to the SAP web portal. All samples are manually transcribed, and 30 per participant are annotated using differential diagnostic pattern dimensions. For purposes of ASR experiments, the participants have been randomly assigned to a training set, a development set for controlled testing of a trained ASR, and a test set to evaluate ASR error rate. Results: The SAP 2023-10-05 Data Package contains the speech of 211 people with dysarthria as a correlate of Parkinson's disease, and the associated test set contains 42 additional speakers. A baseline ASR, with a word error rate of 3.4% for typical speakers, transcribes test speech with a word error rate of 36.3%. Fine-tuning reduces the word error rate to 23.7%. Conclusions: Preliminary findings suggest that a large corpus of dysarthric and dysphonic speech has the potential to significantly improve speech technology for people with disabilities. By providing these data to researchers, the SAP intends to significantly accelerate research into accessible speech technology. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Speech, Language & Hearing Research is the property of American Speech-Language-Hearing Association and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Education Research Complete
FullText Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: ehh
DbLabel: Education Research Complete
An: 180765729
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Community-Supported Shared Infrastructure in Support of Speech Accessibility.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Hasegawa-Johnson%2C+Mark%22">Hasegawa-Johnson, Mark</searchLink><relatesTo>1</relatesTo><i> jhasegaw@illinois.edu</i><br /><searchLink fieldCode="AR" term="%22Xiuwen+Zheng%22">Xiuwen Zheng</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Heejin+Kim%22">Heejin Kim</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Mendes%2C+Clarion%22">Mendes, Clarion</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Dickinson%2C+Meg%22">Dickinson, Meg</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Hege%2C+Erik%22">Hege, Erik</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Zwilling%2C+Chris%22">Zwilling, Chris</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Moore+Channell%2C+Marie%22">Moore Channell, Marie</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Mattie%2C+Laura%22">Mattie, Laura</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Hodges%2C+Heather%22">Hodges, Heather</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Ramig%2C+Lorraine%22">Ramig, Lorraine</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Bellard%2C+Mary%22">Bellard, Mary</searchLink><relatesTo>3</relatesTo><br /><searchLink fieldCode="AR" term="%22Shebanek%2C+Mike%22">Shebanek, Mike</searchLink><relatesTo>4</relatesTo><br /><searchLink fieldCode="AR" term="%22Sari%2C+Leda%22">Sari, Leda</searchLink><relatesTo>4</relatesTo><br /><searchLink fieldCode="AR" term="%22Kalgaonkar%2C+Kaustubh%22">Kalgaonkar, Kaustubh</searchLink><relatesTo>4</relatesTo><br /><searchLink fieldCode="AR" term="%22Frerichs%2C+David%22">Frerichs, David</searchLink><relatesTo>5</relatesTo><br /><searchLink fieldCode="AR" term="%22Bigham%2C+Jeffrey+P%2E%22">Bigham, Jeffrey P.</searchLink><relatesTo>6</relatesTo><br /><searchLink fieldCode="AR" term="%22Findlater%2C+Leah%22">Findlater, Leah</searchLink><relatesTo>6</relatesTo><br /><searchLink fieldCode="AR" term="%22Lea%2C+Colin%22">Lea, Colin</searchLink><relatesTo>6</relatesTo><br /><searchLink fieldCode="AR" term="%22Herrlinger%2C+Sarah%22">Herrlinger, Sarah</searchLink><relatesTo>6</relatesTo>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+Speech%2C+Language+%26+Hearing+Research%22">Journal of Speech, Language & Hearing Research</searchLink>. Nov2024, Vol. 67 Issue 11, p4162-4175. 14p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Community+support%22">Community support</searchLink><br />*<searchLink fieldCode="DE" term="%22Health+services+accessibility%22">Health services accessibility</searchLink><br />*<searchLink fieldCode="DE" term="%22Dysarthria%22">Dysarthria</searchLink><br />*<searchLink fieldCode="DE" term="%22Assistive+technology%22">Assistive technology</searchLink><br />*<searchLink fieldCode="DE" term="%22Speech+disorders%22">Speech disorders</searchLink><br />*<searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br />*<searchLink fieldCode="DE" term="%22People+with+disabilities%22">People with disabilities</searchLink><br /><searchLink fieldCode="DE" term="%22Automatic+speech+recognition%22">Automatic speech recognition</searchLink><br /><searchLink fieldCode="DE" term="%22Cell+phones%22">Cell phones</searchLink><br /><searchLink fieldCode="DE" term="%22Descriptive+statistics%22">Descriptive statistics</searchLink><br /><searchLink fieldCode="DE" term="%22Parkinson's+disease%22">Parkinson's disease</searchLink><br /><searchLink fieldCode="DE" term="%22Personal+computers%22">Personal computers</searchLink><br /><searchLink fieldCode="DE" term="%22Data+analysis+software%22">Data analysis software</searchLink>
– Name: SubjectGeographic
  Label: Geographic Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Illinois%22">Illinois</searchLink><br /><searchLink fieldCode="DE" term="%22United+States%22">United States</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Purpose: The Speech Accessibility Project (SAP) intends to facilitate research and development in automatic speech recognition (ASR) and other machine learning tasks for people with speech disabilities. The purpose of this article is to introduce this project as a resource for researchers, including baseline analysis of the first released data package. Method: The project aims to facilitate ASR research by collecting, curating, and distributing transcribed U.S. English speech from people with speech and/or language disabilities. Participants record speech from their place of residence by connecting their personal computer, cell phone, and assistive devices, if needed, to the SAP web portal. All samples are manually transcribed, and 30 per participant are annotated using differential diagnostic pattern dimensions. For purposes of ASR experiments, the participants have been randomly assigned to a training set, a development set for controlled testing of a trained ASR, and a test set to evaluate ASR error rate. Results: The SAP 2023-10-05 Data Package contains the speech of 211 people with dysarthria as a correlate of Parkinson's disease, and the associated test set contains 42 additional speakers. A baseline ASR, with a word error rate of 3.4% for typical speakers, transcribes test speech with a word error rate of 36.3%. Fine-tuning reduces the word error rate to 23.7%. Conclusions: Preliminary findings suggest that a large corpus of dysarthric and dysphonic speech has the potential to significantly improve speech technology for people with disabilities. By providing these data to researchers, the SAP intends to significantly accelerate research into accessible speech technology. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Journal of Speech, Language & Hearing Research is the property of American Speech-Language-Hearing Association and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=ehh&AN=180765729
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1044/2024_JSLHR-24-00122
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 14
        StartPage: 4162
    Subjects:
      – SubjectFull: Community support
        Type: general
      – SubjectFull: Health services accessibility
        Type: general
      – SubjectFull: Dysarthria
        Type: general
      – SubjectFull: Assistive technology
        Type: general
      – SubjectFull: Speech disorders
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: People with disabilities
        Type: general
      – SubjectFull: Automatic speech recognition
        Type: general
      – SubjectFull: Cell phones
        Type: general
      – SubjectFull: Descriptive statistics
        Type: general
      – SubjectFull: Parkinson's disease
        Type: general
      – SubjectFull: Personal computers
        Type: general
      – SubjectFull: Data analysis software
        Type: general
      – SubjectFull: Illinois
        Type: general
      – SubjectFull: United States
        Type: general
    Titles:
      – TitleFull: Community-Supported Shared Infrastructure in Support of Speech Accessibility.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Hasegawa-Johnson, Mark
      – PersonEntity:
          Name:
            NameFull: Xiuwen Zheng
      – PersonEntity:
          Name:
            NameFull: Heejin Kim
      – PersonEntity:
          Name:
            NameFull: Mendes, Clarion
      – PersonEntity:
          Name:
            NameFull: Dickinson, Meg
      – PersonEntity:
          Name:
            NameFull: Hege, Erik
      – PersonEntity:
          Name:
            NameFull: Zwilling, Chris
      – PersonEntity:
          Name:
            NameFull: Moore Channell, Marie
      – PersonEntity:
          Name:
            NameFull: Mattie, Laura
      – PersonEntity:
          Name:
            NameFull: Hodges, Heather
      – PersonEntity:
          Name:
            NameFull: Ramig, Lorraine
      – PersonEntity:
          Name:
            NameFull: Bellard, Mary
      – PersonEntity:
          Name:
            NameFull: Shebanek, Mike
      – PersonEntity:
          Name:
            NameFull: Sari, Leda
      – PersonEntity:
          Name:
            NameFull: Kalgaonkar, Kaustubh
      – PersonEntity:
          Name:
            NameFull: Frerichs, David
      – PersonEntity:
          Name:
            NameFull: Bigham, Jeffrey P.
      – PersonEntity:
          Name:
            NameFull: Findlater, Leah
      – PersonEntity:
          Name:
            NameFull: Lea, Colin
      – PersonEntity:
          Name:
            NameFull: Herrlinger, Sarah
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 11
              Text: Nov2024
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 10924388
          Numbering:
            – Type: volume
              Value: 67
            – Type: issue
              Value: 11
          Titles:
            – TitleFull: Journal of Speech, Language & Hearing Research
              Type: main
ResultId 1