In July 2003, he obtained a Bachelor of Science degree from the Department of Electronic Science and Engineering of Nanjing University. In July 2008, he received his Ph.D. in signal and information processing from Institute of Acoustics, Chinese Academy of Sciences. During the doctoral period, his research interests were large-scale continuous speech recognition and speech document retrieval (doctoral thesis: Chinese speech retrieval for large-scale telephone conversation, tutor Yan Yonghong). As the backbone of laboratory students, I participated in the 973 sub-project, 863 goal-oriented project and 242 special project of the Ministry of Information Industry, and was responsible for developing a continuous speech recognition engine based on compact state network and a speech keyword retrieval system based on confusion network under the one-way framework and putting it into practical application; After graduating from Ph.D. in July 2008, he directly entered the Computer Application Department of Computer College of Zhejiang University to engage in post-doctoral research for teachers (post-doctoral work report: research on key technologies of intelligent processing of online media, with Professor Zhuang Yueting as co-tutor), and stayed in the school on 20 10 September. During his work in Zhejiang University, his research direction expanded to audio-visual intelligent analysis, cross-media mining and retrieval, and distributed computing. As the person in charge, he has undertaken many projects, such as the national postdoctoral general fund, special fund, the joint project of the Ministry of Education and Microsoft Key Laboratory, and the sub-project of the provincial priority theme social development project. As a young backbone, he has participated in many projects, such as the sub-project of the 973 project, the major research plan of the National Natural Science Foundation, and the major special sub-project of the Nuclear High-tech Fund.