Geometry-aware Deep Learning Methods for Sound Source Localization
About this Topic:
Deep Learning (DL) methods currently obtain state-of-the-art performance in the tasks of positional Sound Source Localization (SSL) and acoustic Direction of Arrival (DOA) estimation. However, most DL methods require matched microphone array geometries between training and testing scenarios, requiring separate models to be trained for different devices. In this webinar, the presenter will present geometry-aware and geometry-agnostic DL approaches for SSL, comparing their advantages and drawbacks, and future research directions.
About the Presenter:
Eric Grinstein received the B.S. degree in computer engineering from PUC-Rio, Brazil in 2019, the M.Eng. degree in electrical engineering at IMT Atlantique, France, in 2019, and the Ph.D. degree in electrical engineering at Imperial College London, U.K. in 2025.
He is currently a Machine Learning Engineer at Bose Corporation, U.K. He was a Research Scientist Intern at Meta Reality Labs in 2024, a visiting researcher at KU Leuven in 2023, and a Data Engineer at Microsoft from 2019 to 2020.
Want to learn more about upcoming events & webinars?
Visit the events section of the Signal Processing website to see all upcoming lectures, workshops, webinars, and more.