AI-Guided Training for Speech Sound Disorder

(GAINS Trial)

Recruiting at 1 trial location

Overseen By Tara McAllister, PhD

Age: < 18

Sex: Any

Trial Phase: Phase 2

Sponsor: New York University

Disqualifiers: Voice disorder, Orthodontia, Hearing loss, Developmental disability, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Prior Safety Data This treatment has passed at least one previous human trial

Compensation: Varies

Number of Visits: Unknown

Duration: 6 weeks

76 Participants Needed

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial explores how artificial intelligence (AI) can assist children with Speech Sound Disorder (SSD) in practicing and improving their speech at home. The study aims to determine if an AI-guided program can enhance the results of previous biofeedback therapy, making speech improvements more sustainable in everyday conversation. Participants will either continue with their regular speech therapy or engage in AI-guided maintenance training with visual-acoustic biofeedback. This trial is suitable for children who speak English as their primary language, have access to a computer and internet, and have previously completed a related speech therapy study. As a Phase 2 trial, this research measures the treatment's effectiveness in an initial, smaller group, offering participants a chance to contribute to advancements in speech therapy.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications. It seems focused on speech therapy and does not mention medication requirements.

What prior data suggests that this AI-guided training is safe for children with speech sound disorder?

Research has shown that AI-guided training with visual and sound feedback is generally safe for treating speech sound disorders. Studies have not reported any safety issues with this type of feedback. This treatment improves speech by providing users with visual and sound cues. It offers a new way to support speech therapy and has been well-received by study participants. ^{1 2 3 4 5}

Why do researchers think this study treatment might be promising for speech sound disorder?

Researchers are excited about AI-guided maintenance training with visual-acoustic biofeedback because it offers a new way to treat Speech Sound Disorder. Unlike traditional speech therapy, which often relies on auditory feedback alone, this method integrates visual-acoustic biofeedback, allowing participants to see and hear their speech patterns in real-time. This innovative approach not only enhances self-monitoring but could also speed up the learning process and improve outcomes by making therapy more interactive and engaging. By leveraging AI, the treatment can also be personalized to better meet individual needs, potentially leading to more effective and lasting improvements in speech.

What evidence suggests that AI-guided maintenance training with visual-acoustic biofeedback is effective for Speech Sound Disorder?

This trial will compare AI-guided maintenance training with visual-acoustic biofeedback to treatment as usual (TAU) for speech sound disorders. Research has shown that visual and sound feedback can improve speech, particularly at the start of treatment. This feedback provides users with visual goals, enabling more effective speech adjustments. Studies have found this method promising for children with speech sound disorders. Early findings suggest that combining artificial intelligence with this feedback could make speech therapy more accessible and effective, allowing practice to continue outside clinic sessions. This approach may help speech improvements carry over into everyday speaking situations. ^{1 3 6 7 8}

Are You a Good Fit for This Trial?

This trial is for children aged 9 to 17 with Speech Sound Disorder who have normal hearing, oral function, and language abilities. They must have completed a previous study (VISIT), have access to a computer with home wifi, speak English as a primary or joint-first language from an early age, and not exhibit severe voice/fluency disorders or developmental disabilities.

Inclusion Criteria

Must pass a pure-tone hearing screening

Must pass a brief examination of oral structure and function

Must demonstrate age-appropriate receptive and expressive language abilities on the Clinical Evaluation of Language Fundamentals-5 (CELF-5)

Exclusion Criteria

Must not exhibit voice or fluency disorder of a severity judged likely to interfere with the ability to participate in study activities

Must not have an existing diagnosis of developmental disability such as cerebral palsy or Down Syndrome

I do not have non-removable braces that cross my palate.

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Treatment

Participants receive AI-guided maintenance training with visual-acoustic biofeedback at home

6 weeks

All sessions conducted online

Follow-up

Participants are monitored for production accuracy and generalization of treatment gains

4 weeks

Pre and post treatment evaluations in laboratory

What Are the Treatments Tested in This Trial?

Interventions

• AI-guided maintenance training with visual-acoustic biofeedback

Trial Overview The study tests AI-guided maintenance training using visual-acoustic biofeedback against the usual treatment methods for improving speech sound generalization in children. It builds on prior research by extending therapy beyond clinical settings into the home environment.

How Is the Trial Designed?

Group I: AI-guided maintenance training with visual-acoustic biofeedback Experimental Treatment 2 Interventions

Participants will receive visual-acoustic biofeedback treatment from a clinician in a private, password-protected WebRTC room.

Group II: Treatment as usual [TAU] Active Control 1 Intervention

Regular community-based care.

Who Is Running the Clinical Trial?

New York University

Lead Sponsor

Trials

249

Recruited

229,000+

Montclair State University

Collaborator

Trials

14

Recruited

1,200+

Syracuse University

Collaborator

Trials

54

Recruited

118,000+

Published Research Related to This Trial

Visual-acoustic biofeedback (VAB) treatment can effectively improve speech outcomes for individuals with speech sound difficulties, particularly in correcting distortions of the /ɹ/ sound.

Successful implementation of VAB relies on key factors such as understanding acoustic representations, selecting appropriate targets and strategies, and providing effective feedback, which together enhance speech sound acquisition and generalization.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Tutorial: Using Visual-Acoustic Biofeedback for Speech Sound Training. Hitchcock, ER., Ochs, LC., Swartz, MT., et al.[2023]

Ultrasound biofeedback therapy (UBT) shows promise in improving speech for children with residual speech sound disorder (RSSD), but it can be complex and demanding, necessitating simpler articulation targets for better understanding.

The study developed an image-analysis program, TonguePART, which successfully quantified tongue movements and distinguished accurate from misarticulated /ɑr/ sounds with up to 85% classification accuracy, highlighting the importance of tongue dorsum and blade movements for effective speech production.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Classification of accurate and misarticulated /&#593;r/ for ultrasound biofeedback using tongue part displacement trajectories. Li, SR., Dugan, S., Masterson, J., et al.[2023]

Citations

1. withpower.com withpower.com/trial/phase-2-speech-sound-disorder-3-2025-3a3a9

AI-Guided Training for Speech Sound Disorder (GAINS Trial) Research shows that visual-acoustic biofeedback can be effective in improving speech sounds, especially in the early stages of treatment, by providing detailed ...

2. pubmed.ncbi.nlm.nih.gov pubmed.ncbi.nlm.nih.gov/36623212/

Using Visual-Acoustic Biofeedback for Speech Sound Training This tutorial summarizes current practices using visual-acoustic biofeedback (VAB) treatment to improve speech outcomes for individuals with speech sound ...

3. artsandsciences.syracuse.edu artsandsciences.syracuse.edu/news-all/news-2024/as-professor-receives-nih-grant-to-study-biofeedback-technologies-for-speech-therapy/

A&S Professor Receives NIH Grant to Study Biofeedback ... The grant will explore the effectiveness of technologies which use visual targets to help people adjust their speech.

4. pubs.asha.org pubs.asha.org/doi/10.1044/2024_AJSLP-23-00448

Artificial Intelligence–Assisted Speech Therapy for /ɹ This feasibility trial describes changes in rhotic production in residual speech sound disorder following ten 40-min sessions including artificial ...

5. scholarworks.sjsu.edu scholarworks.sjsu.edu/cgi/viewcontent.cgi?article=9040&context=etd_theses

A Qualitative Evaluation of Speech Sound Disorder Treatment ... For example, there are recent reports suggesting these children benefit from visual biofeedback and/or visual-acoustic biofeedback in speech therapy (Cleland et ...

6. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC10023147/

Tutorial: Using Visual–Acoustic Biofeedback for Speech ... This tutorial summarizes current practices using visual–acoustic biofeedback (VAB) treatment to improve speech outcomes for individuals with speech sound ...

7. researchgate.net researchgate.net/publication/366985384_Tutorial_Using_Visual-Acoustic_Biofeedback_for_Speech_Sound_Training

Using Visual–Acoustic Biofeedback for Speech Sound ... Purpose This tutorial summarizes current practices using visual–acoustic biofeedback (VAB) treatment to improve speech outcomes for individuals with speech ...

8. bmcpediatr.biomedcentral.com bmcpediatr.biomedcentral.com/articles/10.1186/s12887-024-05364-z

Protocol for visual-acoustic intervention with service delivery ... This project will systematically measure the outcomes of visual-acoustic biofeedback intervention when delivered in-person or online.