Mirror speech using a personalized digital voice for nonfluent aphasia
Mirror Speech Entrainment: A Novel Technique for Voice Personalized Speech Entrainment for Nonfluent Aphasia
This project will test whether using a digitally personalized version of a person's own voice during speech entrainment helps adults with nonfluent aphasia speak more clearly.
Quick facts
| Phase | Not applicable |
|---|---|
| Study type | Interventional |
| Enrollment | 20 (estimated) |
| Ages | 18 Years to 70 Years |
| Sex | All |
| Sponsor | University of South Florida Academic / other |
| Locations | 2 sites (Tampa, Florida and 1 other locations) |
| Trial ID | NCT06829420 on ClinicalTrials.gov |
What this trial studies
This interventional program uses AI voice cloning to create a personalized, digitally altered version of each participant's voice and delivers speech entrainment exercises through a mobile app. Participants complete entrainment tasks at home on smartphones mailed to them, using either the personalized voice or traditional therapist-model prompts (auditory-only or auditory-visual). The study compares language production outcomes between the personalized-voice condition and the traditional entrainment conditions. Eligibility focuses on English-dominant adults aged 18–70 with nonfluent aphasia due to left-hemisphere stroke.
Who should consider this trial
Good fit: Ideal candidates are adults 18–70 who are dominant English speakers with nonfluent aphasia after a left-hemisphere stroke and who can follow app-based instructions at home.
Not a fit: People whose aphasia is due to dementia, Parkinsonism, or other non-stroke causes, or who have severe comprehension problems, major cognitive disabilities, or uncorrected sensory deficits are unlikely to benefit from this approach.
Why it matters
Potential benefit: If successful, the approach could make speech entrainment more effective and comfortable by using a familiar-sounding voice to boost spoken language production.
How similar studies have performed: Traditional speech entrainment using therapist models has helped some people with nonfluent aphasia, but using AI-cloned personalized voices is a novel approach with limited prior clinical evidence.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Adults between the ages of 18-70 years old * Dominant English-speaking * Aphasia due to left hemisphere stroke Exclusion Criteria: * Individuals with aphasia due to other causes such as dementia, Alzheimer's disease and Parkinsonism * Non-dominant English adult speakers * Persons with significant difficulties with language comprehension * Persons with concomitant cognitive disability * Persons with uncorrected sensory deficits.
Where this trial is running
Tampa, Florida and 1 other locations
- University of South Florida — Tampa, Florida, United States (Not_yet_recruiting)
- University of South Florida — Tampa, Florida, United States (Recruiting)
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.