Connecting Concepts from Signal Processing to Embedded Machine Learning with Project-Based Learning

Joseph (Tre) DiPassio III, Research Assistant Professor in the Department of Electrical and Computer Engineering at the University of Rochester

601 Computer Studies Building

In this talk, I discuss how project-based learning has directly influenced my trajectory as an instructor, mentor, and researcher. At a pivotal point in my own education, I decided to pursue a project in which I developed a system for detecting speech discontinuities in media. Through working on this project, I became deeply fascinated with the world of signal processing. This experience laid the foundation for my exploration of concepts such as the spectral properties of human speech, compact feature spaces derived from Mel-frequency cepstral coefficients, and machine learning approaches to pattern recognition. I will discuss how my engagement with these concepts through this project led to my dissertation work in developing directional acoustic sensors, and further led to the development of embedded machine learning tools for anomaly detection and multimodal human-computer interaction systems. My personal experiences with project-based learning ignited a passion that shaped the trajectory of my academic career. I will share research that supports the notion that this style of learning wasn’t just a transformative experience for me but is an effective paradigm in engineering education generally. Finally, I will outline my commitment to incorporating project-based learning into my instructional approach and to creating an environment where students can inspire themselves to engage meaningfully with their studies and pursue paths that challenge and excite them.

Tre DiPassio is a Research Assistant Professor in the Department of Electrical and Computer Engineering at the University of Rochester (UofR). He received his Ph.D. in Electrical and Computer Engineering from the UofR in 2023, and his M.S. and B.S. degrees in Electrical Engineering from the Rochester Institute of Technology in 2018. He is an active instructor and mentor, and was a recipient of the UofR’s Edward Peck Curtis Award for excellence in undergraduate teaching in 2020. His research focuses on the fields of signal processing, acoustics, and embedded machine learning.