Aphasia, Aphasia Non Fluent, Stroke
Conditions
Keywords
Aphasia, Nonfluent aphasia, Speech entrainment, Speech synchronization
Brief summary
The goal of this clinical trial is to test the use of voice personalization through artificial intelligence (AI) voice cloning on speech entrainment tasks to improve language production of persons with aphasia (PWA). The main question the study aims to answer is: \- What is the impact of personalized voice on speech entrainment in PWA compared to traditional speech entrainment? Speech entrainment is a technique used by speech-language pathologists to improve the speech production of PWA. Traditionally, speech therapists act as the model for participants to speak along with to improve their speech production. This study proposes the use of one's own voice (digitally altered) to improve speech production. The study uses a mobile health approach to administer speech entrainment treatment through a mobile app. * Smartphones with the mobile app pre-installed will be mailed to participants at no cost. * Participants will complete treatment in the comfort of their homes. * The experimental treatments involve: mirror speech entrainment (speaking along to one's own voice) and traditional speech entrainment (speaking along to someone else's voice).
Interventions
BEHAVIORALMirror speech entrainment
Speech entrainment with the user's own voice using auditory-only and auditory-visual modalities.
BEHAVIORALTraditional speech entrainment: auditory-only
Traditional speech entrainment (speech entrainment using an external agent's voice) using the auditory-only modality (users only listen and speak along to auditory stimuli)
BEHAVIORALTraditional speech entrainment: auditory-visual
Traditional speech entrainment (speech entrainment using an external agent's voice) using the auditory-visual modality (users listen and speak along to both auditory and visual stimuli (mouth movements)
Sponsors
University of South Florida
Study design
Allocation
RANDOMIZED
Intervention model
PARALLEL
Primary purpose
TREATMENT
Masking
SINGLE (Outcomes Assessor)
Eligibility
Sex/Gender
ALL
Age
18 Years to 70 Years
Healthy volunteers
No
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.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Speaking rate | From enrollment to the end of treatment at 6 weeks | Language production as assessed by number of correct words produced per minute |
Countries
United States
Outcome results
None listed