SPS SLTC/AASP TC Webinar: Neural Acoustic Feedback Cancellation: From Signal Processing to Deep Learning
Date: 18 June 2025
Time: 11:00 AM ET (New York Time)
Presenter(s): Dr. Dong Yu, Dr. Zhang Hao
Abstract
This presentation explores recent advancements in integrating traditional signal processing with deep learning to address the challenges of acoustic feedback cancellation, particularly focusing on acoustic echo and howling suppression. While traditional methods typically rely on adaptive filters to mitigate these issues, their performance is often limited by nonlinear distortions. With the rapid progress in deep learning, numerous studies have proposed solutions that either leverage deep learning independently or combine it with conventional adaptive filtering techniques.
The presentation begins by outlining the fundamental problem of acoustic feedback cancellation, emphasizing its key technical challenges and the complexities involved in real-time processing. Following this, the presenters will introduce several innovative hybrid approaches that integrate deep learning with traditional signal processing methods, delving into their underlying methodologies and evaluating their effectiveness in addressing feedback cancellation issues.
Through theoretical analysis and experimental results, they will discuss the key challenges these methods face in tackling feedback cancellation, as well as their potential and advantages in real-world applications.
Biography
Dong Yu (M’97-SM’06-F’18) received the B.S. degree (with honors) in electrical engineering from Zhejiang University, China, the M.S. degree in computer science from Indiana University at Bloomington, IN USA, the M.S. degree in electrical engineering from the Chinese Academy of Sciences, China and the Ph.D. degree in computer science from the University of Idaho, Idaho, USA.
He is currently a distinguished scientist and vice general manager at Tencent AI Lab. Prior to joining Tencent in 2017, he was a principal researcher at Microsoft Research (Redmond). His research focuses on speech, natural language, and multimodal processing.
Dr. Yu has published two monographs and over 400 papers. His works have been widely cited and recognized by the IEEE Signal Processing Society best transaction paper award in 2013, 2016, 2020, and 2022, the 2021 NAACL best long paper award, the 2022 IEEE Signal Processing Magazine best paper award, the 2022 IEEE Signal Processing Magazine best column award, and the 2023 EMNLP outstanding paper award. He also has been on the editorial boards of many journals and the organizing committees of various conferences. He was the chair of the IEEE Speech and Language Processing Technical Committee between 2021-2022 and the technical co-chair of ICASSP-2021.
Zhang Hao (M’23) received the Ph.D. degree in computer science from the Ohio State University, Columbus, OH USA in 2022. During his doctoral studies, his research focused on deep learning-based echo cancellation and active noise control.
He is currently a senior researcher in the Multimodal Understanding Research Group at Tencent AI Lab (Seattle) since 2022. His research interests include speech enhancement and separation, howling suppression, audio and speech generation, spoken dialogue systems, and other related areas.
