The integration of generative artificial intelligence into educational applications has enhanced personalized and interactive learning experiences, and it shows strong potential to promote young learners language acquisition. However, it is still challenging to ensure consistent and robust performance across different languages and cultural contexts, and kids-friendly design requires simplified instructions, engaging interactions, and age-appropriate scaffolding to maintain motivation and optimize learning outcomes. In this work, we introduce SingaKids, a dialogic tutor designed to facilitate language learning through picture description tasks. Our system integrates dense image captioning, multilingual dialogic interaction, speech understanding, and engaging speech generation to create an immersive learning environment in four languages: English, Mandarin, Malay, and Tamil. We further improve the system through multilingual pre-training, task-specific tuning, and scaffolding optimization. Empirical studies with elementary school students demonstrate that SingaKids provides effective dialogic teaching, benefiting learners at different performance levels.
@article{arxiv.2506.02412,
title = {SingaKids: A Multilingual Multimodal Dialogic Tutor for Language Learning},
author = {Zhengyuan Liu and Geyu Lin and Hui Li Tan and Huayun Zhang and Yanfeng Lu and Xiaoxue Gao and Stella Xin Yin and He Sun and Hock Huan Goh and Lung Hsiang Wong and Nancy F. Chen},
journal= {arXiv preprint arXiv:2506.02412},
year = {2025}
}