AIED

Benchmarking Scientific Formula Vocalization in Large Speech Language Models Toward Accessible Learning

Fri Jul 3, 9:00 AM–9:25 AM · North 203

Part of Speech and Multimodal Learning Analytics in Education

Multimodal Learning Analytics Equity, Fairness & Inclusion Science & STEM Inquiry

★ Notable speakers

Zitao Liu ★ — Deep learning for knowledge tracing; pyKT benchmark library; AI-powered adaptive learning at scale

Benchmarks how well large speech-language models vocalize scientific formulas, with implications for accessible learning for students with visual impairments.

Authors

Xueyi Li, Tianqiao Liu, Jiaqi Zheng, Zitao Liu, Yongdong Wu, Weiqi Luo