Xuzhou Ye
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xuzhou Ye has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Qiuqiang Kong
The Chinese University of Hong Kong Hong Kong China
2 shared publications - Shilei Liu
Key Laboratory of Modern Acoustics (MOE), Department of Physics, Collaborative Innovation Centre of Advanced Microstructure, Nanjing University, Nanjing 210093, China
2 shared publications - Hongming Shan
Fudan University, Shanghai, China
1 shared publication - Ju-Chiang Wang
Beijing ByteDance Technology Co. Ltd.,Shanghai,China,201102
1 shared publication - Jun-Jie Shi
State Key Laboratory for Artificial Microstructures and Mesoscopic Physics, School of Physics, Peking University Yangtze Delta Institute of Optoelectronics, Peking University, Beijing 100871, China
1 shared publication - Junjie Shi
Beijing ByteDance Technology Co. Ltd.,Shanghai,China,201102
1 shared publication
Latest Publications
- 29 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/CAA Journal of Automatica Sinica
- Vol. 11 (2) , 502-513
End-to-End Paired Ambisonic-Binaural Audio Rendering
Binaural rendering is of great interest to virtual reality and immersive media. Although humans can naturally use their two ears to perceive the spatial information contained in sounds, it is a challenging task for machines to achieve binaural rendering since the description of a sound field often requires multiple channels and even the metadata of the sound sources. In addition, the perceived sound varies from person to person even in the same sound field. Previous methods generally rely on individual-dependent head-related transferred function (HRTF) datasets and optimization algorithms that act on HRTFs. In practical applications, there are two major drawbacks to existing methods. The first is a high personalization cost, as traditional methods achieve personalized needs by measuring HRTFs. The second is insufficient accuracy because the optimization goal of traditional methods is to retain another part of information that is more important in perception at the cost of discarding a part of the information. Therefore, it is desirable to develop novel techniques to achieve personalization and accuracy at a low cost. To this end, we focus on the binaural rendering of ambisonic and propose 1) channel-shared encoder and channel-compared attention integrated into neural networks and 2) a loss function quantifying interaural level differences to deal with spatial information. To verify the proposed method, we collect and release the first paired ambisonic-binaural dataset and introduce three metrics to evaluate the content information and spatial information accuracy of the end-to-end methods. Extensive experimental results on the collected dataset demonstrate the superior performance of the proposed method and the shortcomings of previous methods.
- 29 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/CAA Journal of Automatica Sinica
- Vol. 11 (2) , 502-513
End-to-End Paired Ambisonic-Binaural Audio Rendering
Binaural rendering is of great interest to virtual reality and immersive media. Although humans can naturally use their two ears to perceive the spatial information contained in sounds, it is a challenging task for machines to achieve binaural rendering since the description of a sound field often requires multiple channels and even the metadata of the sound sources. In addition, the perceived sound varies from person to person even in the same sound field. Previous methods generally rely on individual-dependent head-related transferred function (HRTF) datasets and optimization algorithms that act on HRTFs. In practical applications, there are two major drawbacks to existing methods. The first is a high personalization cost, as traditional methods achieve personalized needs by measuring HRTFs. The second is insufficient accuracy because the optimization goal of traditional methods is to retain another part of information that is more important in perception at the cost of discarding a part of the information. Therefore, it is desirable to develop novel techniques to achieve personalization and accuracy at a low cost. To this end, we focus on the binaural rendering of ambisonic and propose 1) channel-shared encoder and channel-compared attention integrated into neural networks and 2) a loss function quantifying interaural level differences to deal with spatial information. To verify the proposed method, we collect and release the first paired ambisonic-binaural dataset and introduce three metrics to evaluate the content information and spatial information accuracy of the end-to-end methods. Extensive experimental results on the collected dataset demonstrate the superior performance of the proposed method and the shortcomings of previous methods.
- Open Access
Neural Sound Field Decomposition with Super-resolution of Sound Direction
Sound field decomposition predicts waveforms in arbitrary directions using signals from a limited number of microphones as inputs. Sound field decomposition is fundamental to downstream tasks, including source localization, source separation, and spatial audio reproduction. Conventional sound field decomposition methods such as Ambisonics have limited spatial decomposition resolution. This paper proposes a learning-based Neural Sound field Decomposition (NeSD) framework to allow sound field decomposition with fine spatial direction resolution, using recordings from microphone capsules of a few microphones at arbitrary positions. The inputs of a NeSD system include microphone signals, microphone positions, and queried directions. The outputs of a NeSD include the waveform and the presence probability of a queried position. We model the NeSD systems respectively with different neural networks, including fully connected, time delay, and recurrent neural networks. We show that the NeSD systems outperform conventional Ambisonics and DOANet methods in sound field decomposition and source localization on speech, music, and sound events datasets. Demos are available at https://www.youtube.com/watch?v=0GIr6doj3BQ.
Open AccessNeural Sound Field Decomposition with Super-resolution of Sound Direction
Sound field decomposition predicts waveforms in arbitrary directions using signals from a limited number of microphones as inputs. Sound field decomposition is fundamental to downstream tasks, including source localization, source separation, and spatial audio reproduction. Conventional sound field decomposition methods such as Ambisonics have limited spatial decomposition resolution. This paper proposes a learning-based Neural Sound field Decomposition (NeSD) framework to allow sound field decomposition with fine spatial direction resolution, using recordings from microphone capsules of a few microphones at arbitrary positions. The inputs of a NeSD system include microphone signals, microphone positions, and queried directions. The outputs of a NeSD include the waveform and the presence probability of a queried position. We model the NeSD systems respectively with different neural networks, including fully connected, time delay, and recurrent neural networks. We show that the NeSD systems outperform conventional Ambisonics and DOANet methods in sound field decomposition and source localization on speech, music, and sound events datasets. Demos are available at https://www.youtube.com/watch?v=0GIr6doj3BQ.