Academic Lecture—Distributed Microphone Array Sound Pickup Theory and Methods

Author：Administrator Source：website Time：2025-06-15 12:00:00

Presentation Time: 9:30 AM, June 15, 2025 (Sunday)

Venue: Conference Room B621, School of Electronic Information, Wuhan University (Yu Gang & Song Xiao Building)

Presentation Title: Sound Pickup Theory and Methods of Distributed Microphone Arrays

Presentator: Associate Professor Zhang Jie

Inviter: Professor Huang Gongping

Abstract:

After decades of development, microphone array technology has matured and is widely used in human-computer interaction systems such as video conferencing, smart TVs, mobile phones, and hearing aids. However, in real-world noisy or long-distance interaction scenarios, the sound pickup quality of traditional microphone arrays with limited array structures is difficult to guarantee. With the widespread use of wireless smart terminal devices, distributed microphone arrays (or wireless acoustic sensor networks) offer more possibilities for improving the sound pickup quality of complex open-domain voice interaction systems, offering advantages in array organization, user experience, and sound field coverage. In recent years, distributed microphone arrays have demonstrated promising application potential in many voice interaction tasks, essentially achieving full coverage of traditional microphone array voice tasks. This report will focus on summarizing the current sound pickup theory and application methods of distributed microphone arrays, including their application background, array organization principles, and evaluation of microphone node utility. It will also illustrate their application methods in conjunction with downstream speech tasks. Finally, the report will briefly discuss the key challenges and development trends in the practical application of distributed microphone arrays.

About the presenter:

Zhang Jie, an associate professor at the School of Information Science and Technology at the University of Science and Technology of China (USTC), works at the National Engineering Research Center for Speech and Language Information Processing (NSLP). His research focuses on distributed microphone array speech processing, brain-inspired auditory speech enhancement and understanding, and their applications in automotive, home, and hearing aid environments. He has published over 80 high-quality academic papers in renowned academic journals and conferences, including 20 IEEE Transactions on Signal Processing papers as first or corresponding author and over 40 papers at leading conferences in the fields of artificial intelligence and speech technology. His paper won the Best Paper Award at IEEE-SAM 2018, the flagship conference in signal processing. He has led his team to win six major international academic competitions in the field of speech technology and received the 2023 China Industry-University-Research Collaboration Innovation Achievement Award. He is the principal investigator of several important projects, including the National Natural Science Foundation of China, the Chinese Academy of Sciences' C-type Pioneer Special Project, and the Anhui Provincial Major Science and Technology Research Project. He is currently a senior member of the Institute of Electrical and Electronics Engineers, a member of the China Computer Federation (CCF) and the Chinese Society of Acoustics, and an executive member of the CCF Speech, Dialogue and Hearing Committee. He serves as an associate editor for the top journal in the field of speech, IEEE Transactions on Audio, Speech and Language Processing (TASLPRO), and the top journal in signal processing, Elsevier Signal Processing.