A Foundations in Speech Processing and Multimodal Intelligence

A Foundations in Speech Processing and Multimodal Intelligence
Share this


Talk details

Title: A Foundations in Speech Processing and Multimodal Intelligence
Speaker: Girish, B.Tech. student (CSE, AI-ML Honors), UPES, India
Date: 5th April 2026
Time: 11:00 AM (IST)

Abstract and Speaker’s bio:

Most researchers find their footing in grad school. Girish didn’t wait. A final-year undergraduate at UPES, he has spent the last two years working across speech processing, multimodal learning, and trustworthy AI β€” collaborating with research groups at IIIT-Delhi, Ulster University, and industry labs, publishing at INTERSPEECH, ICASSP, and EACL.

In this talk, he will share his undergraduate research journey, key projects, and lessons from working across academic and industry labs, offering insights into building a meaningful path in speech and multimodal AI.

Contact: