Desinta Yamasan Rusli
Unknown Affiliation

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

TalkieBuddy : Generative AI-Driven Interactive Doll for Advancing Children's Verbal Skills Desinta Yamasan Rusli; King, Chintya Angel; Silver, Charlene; Priscilla, Priscilla; Ade Maulana
SATESI: Jurnal Sains Teknologi dan Sistem Informasi Vol. 5 No. 2 (2025): Oktober 2025
Publisher : Yayasan Pendidikan Penelitian Pengabdian ALGERO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54259/satesi.v5i2.5769

Abstract

Speech delay remains a major developmental issue among preschool children, with one contributing factor being parents’ limited time to provide consistent language stimulation. This study developed TalkieBuddy, an interactive teddy bear powered by Internet of Things technology and generative artificial intelligence, designed to stimulate children’s speaking skills while enhancing parental involvement. The system captures children’s speech through a microphone, converts it into text using a speech-to-text module, processes it with a large language model (LLM) enriched by educational and psychological literature, and generates responses that are converted back into speech via text-to-speech. All interactions are synchronized with a mobile application, enabling parents to monitor progress through a dashboard, manage child profiles, adjust conversational styles, and access parenting articles. Functional testing confirmed that communication between the device, cloud services, and mobile application operated as intended, with minor limitations in noisy environments. Field trials involving seven preschool children, three parents, and four teachers demonstrated increased speaking confidence, more active responses, and significant parental benefits through the monitoring feature. This study concludes that TalkieBuddy has strong potential as an innovative solution for early language stimulation while reducing children’s reliance on screen-based devices.