MORA: AI-Mediated Story-Based practice for Speech Sound Disorder from Clinic to Home

Sumin Hong, Xavier Briggs, Qingxiao Zheng, Rafiah Ansari, Yao Du, Jinjun Xiong, Toby Jia-Jun Li

Keywords: speech sound disorder, interactive storytelling, expert-in-the-loop, AI-assisted practice

Abstract:

Speech sound disorder (SSD) is common in preschool children, yet effective treatment depends on frequent practice and generalization beyond the clinic. Existing home-practice tools often lack interactivity and provide limited support for clinician oversight, reducing engagement and alignment with therapy plans.
We present MORA, an AI-mediated, story-based home-practice system that embeds target sounds in character-driven conversations and prompts children to speak to advance the narrative. MORA provides multimodal cues and feedback to support independent or caregiver-assisted practice, and an expert-in-the-loop workflow that lets SLPs configure targets, review logged speech (with phoneme-level scoring), and adjust plans asynchronously.
A formative study with six licensed SLPs informed the design, and an expert review with seven SLPs indicated alignment with articulation-based treatment and potential to improve engagement, literacy-oriented practice, and continuity between clinic and home.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 47