Late talking children are at risk of ongoing language impairment. This intervention study replicated and extended research from Mary Alt and colleagues from the University of Arizona, based on cross-situational statistical learning principles. Three late talking children (age 24–32 months) were enrolled into the concurrent multiple baseline single-case experimental intervention study. The intervention consisted of 16 sessions over eight/nine weeks, including 10–11 pairs of target and control words (three per session). Children heard the target words a minimum of 64 times per session, in sentences with high linguistic variability in varied play activities. All children increased production of target words and expressive vocabulary, with statistically significant differences between word acquisition in baseline and intervention phases. One of the three children learnt statistically significantly more target words than control words.The results replicated the findings of previous research for some but not all of the participants, providing individual evidence that this approach has promise as a therapy technique for late talking children.

1. Treatments based on cross-situational statistical learning can increase the expressive vocabulary of some children beyond the typical rates of language growth for late talking monolingual English speaking toddlers. 2. CSSL principles include clinicians speaking using a high dose of target words paired with varied physical exemplars using complete sentences which have syntactic variability. 3. Research of this treatment approach is gaining support from individual case studies alongside group comparisons from institutions in the United States, Australia and Singapore.