After processes including application, college recommendation, review by the evaluation committee, and public announcement, Wang Shuai, an appointed associate professor from our college, has been awarded the 2025 Nanjing University Xiaomi Young Scholar - Science and Technology Innovation Award!
This award was jointly established by the Beijing Xiaomi Foundation and the Nanjing University Education Development Foundation. It aims to encourage and support our university's young talents to focus on the world's scientific and technological frontiers and national major needs, actively engaging in scientific exploration and technological innovation for the future information technology industry. In 2025, this honor was bestowed upon only six faculty members across the entire university.
Winner's Profile
Wang Shuai Associate Professor on Tenure Track
Wang Shuai is a Distinguished Professor, focusing his research on intelligent audio signal processing, encompassing multimodal acoustic signals such as speech, audio events, and music. He received his B.E. degree from Northwestern Polytechnical University in 2014 and his Ph.D. degree from Shanghai Jiao Tong University in 2020. Previously, he served as an Associate Research Fellow at the Shenzhen Institute of Big Data and as a Senior Researcher at Tencent.As the first author or corresponding author, he has published over 40 papers in top-tier conferences and journals such as ICASSP and Interspeech, and has been granted more than 10 patents. He has led championship-winning teams in several international challenges, including VoxSRC 2019, DIHARD 2019, and NIST SRE 2024, and received awards such as the Best Paper and Best Student Paper at ISCSLP 2024.He initiated the open-source tools WeSpeaker and WeSep, whose pre-trained models exceed 10 million monthly downloads on Hugging Face, seeing widespread adoption in both academic and industrial communities. He currently leads multiple research projects, including a Young Scientist Fund from the National Natural Science Foundation of China, a sub-project of the Yangtze River Delta Science and Technology Innovation Community Joint Research Program, an Open Project from the MOE Key Lab of Artificial Intelligence, and a CCF-Netease Leihuo Innovation Fund.He maintains close collaboration with renowned domestic and international companies and research institutes, actively recommending students for internships at leading industry players like Tencent, ByteDance, Xiaomi, NetEase, and Meta FAIR. Several of his students have been successfully selected for elite talent programs such as the Tencent Rhino-Bird Program and the ByteDance TopSeed Program.
Summary of Achievements
Speaker-Centered Voice Modeling Algorithms and Tools
This work addresses the fundamental scientific question of how to stably and scalably acquire and utilize speaker information in complex, open environments. It systematically proposes a series of solutions encompassing representation learning, robust modeling, and a tooling closed-loop. These contributions have led to technological breakthroughs from theory to engineering, significantly pushing the performance limits and enhancing the reproducibility of both speaker recognition and multi-speaker processing tasks.
