Bing Yang
Open Laboratory on Human Robot Interaction, Peking University (PKU), China
Research Interests: Sound source localization, audio signal processing, deep learning
Email: bingyang@pku.sz.edu.cn
Personal: Google Scholar, Research Gate, GitHub, ORCID
Ph.D. in Computer Applied Technology, Sep. 2015 ~ Jan. 2022
School of Electronics Engineering and Computer Science, Peking University (PKU), China
Thesis: Research on Sound Source Localization for Robot Auditory System in Complex Scenes
Supervisor: Prof. Hong Liu
B.Eng. in Automation, Sep. 2011 ~ Jun. 2015
School of Automation, University of Science and Technology Beijing (USTB), China
Top 1% student
A direct-path relative transfer function learning based sound source localization method is proposed to deal with the problem that localization features are easily distorted by noise and reverberation.
It embeds binaural signals to a real-valued direct-path feature space, which disentangles localization cues from other factors including noise, reverberation, etc.
The proposed method owns a strong robustness for sound source localization, and a good generalization ability for unseen binaural arrays.
Enhancing direct-path relative transfer function using deep neural network for robust sound source localization. [paper]
Bing Yang, Runwei Ding, Yutong Ban, Xiaofei Li, Hong Liu.
CAAI Transactions on Intelligence Technology, vol. 7, no. 3, pp. 446-454, 2022.
A time-frequency-wise spatial spectrum clustering based multiple sound source counting and localization method is proposed to solve the problem that signals of multiple sources are mixed and the number of sources is unknown.
Without the priori of source number, it obtains the spatial spectrum clusters of multiple sources by iteratively detecting new sound source and adjusting the dominance association between sources and spatial spectra.
The proposed method achieves a superior performance for joint sound source counting and localization, and can localize sources with small angular separation.
A direct-path phase difference learning based multiple moving sound source localization method is proposed to deal with the problem that the position of moving sources is time-varying and sources are intermittently sounding.
It learns competing and time-varying direct-path phase differences for multiple moving sources，and avoids the problem of assignment ambiguity and uncertain output dimension encountered by the multi-target regression framework.
The proposed method is superior for the azimuth and elevation estimation of multiple moving sources, and the constructed spatial spectrum exhibits reliable peaks around the actual directions of sources.
A continuous multiple sound source localization method and device based on signal subspace similarity spectrum and particle filter.
[一种基于信号子空间相似度谱和粒子滤波器的多声源连续定位方法和装置 ]
Hong Liu, Bing Yang, Haipeng Lan, Cheng Pang.
China Invention Patent. Patent number: ZL201810752391.0. Application date: Jul. 10, 2018. Date of authorized announcement : Apr. 15, 2022.
A multiple moving sound source localization method and system based on spatial and spectral information modelling.
[一种基于空间和频谱时序信息建模的多移动声源定位方法和系统 ]
Hong Liu, Bing Yang, Yidi Li.
China Invention Patent. Application number: 202210137621.9, Application date: Feb. 15, 2022.
Awards
Merit Student, Learning Excellence Award, Excellent Scientific Research Award, Peking University, Sep. 2015 ~ Jan. 2022
Outstanding Graduates, Merit Student, Beijing, Sep. 2011 ~ Jun. 2015
President Medal, Merit Student, Outstanding Student Leaders, University of Science and Technology Beijing, Sep. 2011 ~ Jun. 2015
Scholarship
Founder Scholarship, Peking University, Sep. 2015 ~ Jan. 2022
National Scholarship, National Encouragement Scholarship, Ministry of Education of P.R.China, Sep. 2011 ~ Jun. 2015
‘Guanzhi’ Scholarship, University of Science and Technology Beijing, Sep. 2011 ~ Jun. 2015