LO
CapabilityCognitive automation2024-08-22
AI ran children's speech drill practice after a clinician led the preparation, and its judgements of each attempt largely matched a clinician's, a five-child ChainingAI study found
Speech-language pathologist / speech and language therapistoccupation page →
Event date / reported
2024-08-22
Evidence stage
CapabilityA demo, benchmark or paper shows the task can be done. Updates what the technology can do — not what employers will do.
Tasks this bears on
Assessing communication and swallowing
Testing speech, language, voice and swallowing, deciding what is wrong and setting goals.
Still human-led≈ Platform inference
Delivering therapy and practice
Running therapy sessions and setting the repetitive practice that rebuilds words, sounds and sentences.
Being augmented✓ Evidence-backed
Where this applies
United States, five children with residual speech sound disorder. Pre-practice activities were led by a human clinician and drill-based practice was automated by ChainingAI; listeners heard more accurate /ɹ/ after 30 minutes of practice without a clinician, and the AI's agreement with clinician ratings was largely within the range of human-human agreement for four of five children. The authors evaluated their own tool.
What this means
AI can run and score simple speech drills, but only after a clinician sets up the practice.
What it does not yet show
Five children and one speech sound, evaluated by the tool's developers.
What you can check
Open PubMed 39173110 (AJSLP, 2024) and find "automated by ChainingAI".
Does it change the assessment?
No — and this stage does not move it either. A "Capability" record is real evidence, but it does not upgrade a task judgement on its own. The 2 linked judgements above stand where they were.
Source
Benway NR, Preston JL — Artificial Intelligence-Assisted Speech Therapy for /ɹ/: A Single-Case Experimental Study, American Journal of Speech-Language Pathology (published 22 August 2024; PubMed 39173110) · verified 2026-10-01 · Claude (VOLO agent) · interpreted 2026-10-01 · Claude (VOLO agent)
Primary source — published by the party that did this, or the authority of record. No co-signature needed.