PAIR Distinguished Lecture : Machine Listening : Extending AI from Vision to Sound and Vibration Sensing

On 23 April 2026, Prof. ZHANG Jie, Chair Professor in Faculty of Business for Science and Technology, University of Science and Technology of China, delivered a PAIR Distinguished Lecture titled “Machine Listening: Extending AI from Vision to Sound and Vibration Sensing” at the PolyU campus. The lecture attracted almost 100 scholars, researchers and students onsite, and nearly 16,000 online viewers across various social media platforms to explore how the emerging field of “machine listening” is transforming urban monitoring, disaster prevention, and infrastructure safety. Prof. Zhang opened the lecture by outlining the major challenges in today’s science and technology. He noted that while AI has reached significant maturity in visual perception, sound and vibration data remain “largely underutilised” in the digital era. He emphasised that machine learning in the domain of sound and vibration sensing is still at an early stage, with vast development potential ahead. While sharing technical insights, Prof. Zhang also reflected on his life and research journey. He remarked, “Only by fully committing myself and giving it everything I had did I discover how fascinating a discipline could be.” He emphasised that true excellence comes through continuous learning and self‑improvement. Technological innovation is now driven by cross‑disciplinary collaboration and collective progress, rather than individual heroism.
To illustrate how machine listening can be translated from concept to practice, Prof. Zhang presented several innovative real-world cases where sound sensing complements visual systems. Among them, he highlighted the “CitySeis” project in Hefei, where approximately 50,000 seismic sensors have been deployed to achieve citywide coverage, enabling continuous monitoring of subsurface structural changes and subway safety, and providing critical information beyond visual perception. He presented applications of “RoadSeis” in digital traffic systems and weight‑in‑motion sensing, showing how vibration signals can predict vehicle weight and assess road health. These examples demonstrated that machine listening can surpass visual technologies, offering a fuller picture of infrastructure conditions above and below ground.
Event date: 23/4/2026
Speaker: Prof. ZHANG Jie
Hosted by: PolyU Academy for Interdisciplinary Research