Speech Accessibility Project
SAP
People With Speech Disabilities Contributing Speech Samples for Improved Accessibility of Speech-Enabled Devices
1 other identifier
observational
485
1 country
2
Brief Summary
The goal of the Speech Accessibility Project at the University of Illinois Beckman Institute (https://speechaccessibilityproject.beckman.illinois.edu) is to collect, annotate, and curate a shared database of speech samples from people with atypical speech, and share this data set with researchers at other organizations. This two-year project plans to collect 1,200,000 speech samples from 2,000 people, each of whom will provide 600 samples. In Year 1, the initial focus will be people with Parkinson's. In Year 2, four more etiologies of interest will be recruited: Amyotrophic Lateral Sclerosis (ALS), Cerebral Palsy (CP), Down Syndrome (DS), and Stroke. UIUC will build an open-source software infrastructure to collect annotated speech samples and share these data in an appropriately secure fashion with researchers from our partner technology companies (and eventually, other organizations as well) so that they can use these data to improve their automatic speech recognition algorithms. This project promotes diversity, equity, and inclusion by helping technology companies to fully support all types of speech, and it is also more efficient and less burdensome for these specialized patient populations to have one centralized "collector" of speech samples.
Trial Health
Trial Health Score
Automated assessment based on enrollment pace, timeline, and geographic reach
participants targeted
Target at P75+ for all trials
Started Mar 2023
Typical duration for all trials
2 active sites
Health score is calculated from publicly available data and should be used for screening purposes only.
Trial Relationships
Click on a node to explore related trials.
Study Timeline
Key milestones and dates
Study Start
First participant enrolled
March 15, 2023
CompletedFirst Submitted
Initial submission to the registry
May 24, 2023
CompletedFirst Posted
Study publicly available on registry
June 5, 2023
CompletedPrimary Completion
Last participant's last visit for primary outcome
March 29, 2025
CompletedStudy Completion
Last participant's last visit for all outcomes
July 31, 2025
CompletedAugust 17, 2025
August 1, 2025
2 years
May 24, 2023
August 12, 2025
Conditions
Outcome Measures
Primary Outcomes (1)
Recorded Speech
Each participant records 600 sentences: 480 read sentences, and 120 spontaneous sentences recorded in response to 30 prompts.
3-7 hours, self-paced
Eligibility Criteria
People currently residing in the United States or Canada, excluding the states of Washington, Texas, or Illinois, with speech disability related to a neuromotor disorder.
You may qualify if:
- Adult (age \>= 18 years)
- Self-reported diagnosis of Parkinson's Disease, ALS, CP, DS, or Stroke
- Reads and speaks English in the form of complete sentences
- Has a valid email address
- Ability to access web browser to participate in study
You may not qualify if:
- Is a resident of the State of Washington, Texas, or Illinois (because these states have privacy laws that would not allow us to collect 'voice prints')
- If quality control screening of initial speech samples "fails" because of poor data quality (e.g., poor quality recording environment, or person's speech is "too typical" and not sufficiently interesting to continue collecting)
Contact the study team to confirm eligibility.
Sponsors & Collaborators
- University of Illinois at Urbana-Champaignlead
- LSVT Globalcollaborator
- Amazon, Inc.collaborator
- Apple Inc.collaborator
- Google LLC.collaborator
- Meta Platforms, Inc.collaborator
- Microsoft Corporationcollaborator
Study Sites (2)
LSVT Global
Denver, Colorado, 80204, United States
University of Illinois at Urbana-Champaign
Urbana, Illinois, 61801, United States
Related Links
MeSH Terms
Conditions
Condition Hierarchy (Ancestors)
Study Officials
- PRINCIPAL INVESTIGATOR
Mark A Hasegawa-Johnson, Ph.D.
University of Illinois at Urbana-Champaign
Study Design
- Study Type
- observational
- Observational Model
- ECOLOGIC OR COMMUNITY
- Time Perspective
- CROSS SECTIONAL
- Target Duration
- 21 Days
- Sponsor Type
- OTHER
- Responsible Party
- SPONSOR
Study Record Dates
First Submitted
May 24, 2023
First Posted
June 5, 2023
Study Start
March 15, 2023
Primary Completion
March 29, 2025
Study Completion
July 31, 2025
Last Updated
August 17, 2025
Record last verified: 2025-08
Data Sharing
- IPD Sharing
- Will share
- Shared Documents
- ICF
- Time Frame
- Data will be available to sponsoring organizations beginning in June 2023. Data will be available to other research organizations beginning in April 2024. Data will be available to other research organizations in perpetuity; a standing review committee will be established at the University of Illinois to review applications for access to this dataset at any time in the future.
- Access Criteria
- Before any research institution is permitted to receive any speech audio recordings, they will be required to sign a data use agreement. Key terms of the data use agreement will include commitments that the research institution (a) is an organization or individual with the legal status necessary to sign a contract, (b) will not make the speech audio recordings available to any individual who is not bound by the member's signature on the data use agreement, (c) will store the data in a secure fashion to prevent data theft, and (d) will not seek to identify any of the participants.
Participant speech data, and text transcripts created by University of Illinois annotators, will be distributed. Each data distribution will consist of a single archive file, compressed and encrypted using a secure key technology, so that it can only be decompressed by individual researchers who have been authorized under the terms of the data use agreement. Data distributions to coalition partners will never contain any information contributed by a participant other than their recorded speech samples.