Shichao Hu is an Associate Professor and Master's Supervisor at the Center for Auditory and Language Intelligence, School of Future Science and Engineering, Soochow University. He received his bachelor's degree from Beijing University of Posts and Telecommunications and his Ph.D. from Tohoku University, Japan. His main research interests include spatial hearing and intelligent acoustics. He has worked on audio and speech research and product development at Huawei, Tencent Music, Facebook, and RION (Japan).
Auditory spatial intelligence and language interaction capabilities are essential supports for embodied intelligence and next-generation auditory and language intelligence systems. How to bridge hardware differences across audio devices and achieve transfer and generalization of spatial hearing capabilities is an important problem in this field. This talk focuses on unified spatial sound field representation for heterogeneous microphone arrays, introducing our recent progress in sound field encoding and sound source localization. We discuss research approaches that integrate acoustic mechanisms with data-driven learning to improve cross-device generalization, and outline applications in robot hearing, smart wearables, and spatial audio interaction.