Published multiple papers on educational data mining, multi-modal learning, automatic speech recognition, etc., such as 'Improving Named Entity Transcription with Contextual LLM-based Revision', 'Multi-modal Speech Transformer Decoders: When Do Multiple Modalities Improve Accuracy?' and more.
Research Experience
Leads several research projects, including the NSF-funded project on developing new scientific instruments for classroom observation using a multi-modal machine learning approach, and the AI Institute for Student-AI Teaming (iSAT) located at CU Boulder, among others.
Background
Research Interests: Applied machine learning, speech and speaker recognition, educational data mining, AI for education, few-shot learning, emotion recognition; Position: Associate Professor, Department of Computer Science, and Learning Science & Technologies (LST)