Self-Supervised App-Based Speech Training for Children With Speech Sound Disorder-A Single-Case Experimental Design Study.
Sofia Strömbergsson, Ella Edlund, Magdalena Pettersson and 2 others
PMID 41327930WHAT IT FOUND
Four Swedish children with speech sound disorder showed no clear improvement in targeted sounds after three weeks of home app training.
Small trained-word gains occurred in some children, but the app's star feedback did not match clinicians' ratings.
Key findings
01Adam showed slight improvement on trained words but no positive effect on untrained words.
02Benjamin, Carl and Doris showed no positive effect of the app on target sound accuracy.
03The app's star feedback did not correspond with clinicians' assessment of target accuracy.
STILL TO COME
How it was doneWhat they foundWhat it means for SLPs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
The study included only four children, so it cannot show how many children would respond. Training lasted only three weeks and was unsupervised at home. The app recorded only 7.2 to 14.0 production efforts per session, while the paper cites a recommendation of 50 to 100 production efforts per session. Technical problems caused missing recordings from practice sessions. The outcome was scored only as target accurate or not, which may miss subtle progress. Speech perception and stimulability were not fully assessed, and the intelligibility questionnaire was not distributed. The children were not receiving speech therapy during the study, so it does not show how the app works alongside therapy.
Declared interests
NordForsk funded the study under project number 103893. The authors report no conflicts of interest.
The easy way to misread this
Do not conclude that app-based speech training is ineffective for all children with speech sound disorder. This study used only four children, three weeks, low dose and little supervision, so it mainly shows this specific delivery did not work.
Summarised by AI from the full paper, without a clinician reviewing it. Check it against the source before it changes what you do. Read it on PubMed →