Publications

You can also visit Google Scholar for more information.

2023

1. CSMT

   

   High Quality Speech Restoration from Device Colorated and Reverberated Speech

   Xiguang Zheng, Xinlei Ren, Lianwu Chen, Chenglin Xu, Yaodu Wei, Chen Zhang, Liang Guo, and Bing Yu

   In National Conference on Sound and Music Technology, 2023

   Bib HTML

   @inproceedings{zheng2023high,
     title = {High Quality Speech Restoration from Device Colorated and Reverberated Speech},
     author = {Zheng, Xiguang and Ren, Xinlei and Chen, Lianwu and Xu, Chenglin and Wei, Yaodu and Zhang, Chen and Guo, Liang and Yu, Bing},
     booktitle = {National Conference on Sound and Music Technology},
     pages = {73--83},
     year = {2023},
     organization = {Springer},
   }

2022

1. ICASSP

   

   L3DAS22 challenge: Learning 3D audio sources in a real office environment

   Eric Guizzo, Christian Marinoni, Marco Pennese, Xinlei Ren, Xiguang Zheng, Chen Zhang, Bruno Masiero, Aurelio Uncini, and Danilo Comminiello

   In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022

   arXiv Bib

   @inproceedings{guizzo2022l3das22,
     title = {L3DAS22 challenge: Learning 3D audio sources in a real office environment},
     author = {Guizzo, Eric and Marinoni, Christian and Pennese, Marco and Ren, Xinlei and Zheng, Xiguang and Zhang, Chen and Masiero, Bruno and Uncini, Aurelio and Comminiello, Danilo},
     booktitle = {ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
     pages = {9186--9190},
     year = {2022},
     organization = {IEEE},
   }

2. ICASSP

   

   A two-step backward compatible fullband speech enhancement system

   Xu Zhang, Lianwu Chen, Xiguang Zheng, Xinlei Ren, Chen Zhang, Liang Guo, and Bing Yu

   In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022

   arXiv Bib

   @inproceedings{zhang2022two,
     title = {A two-step backward compatible fullband speech enhancement system},
     author = {Zhang, Xu and Chen, Lianwu and Zheng, Xiguang and Ren, Xinlei and Zhang, Chen and Guo, Liang and Yu, Bing},
     booktitle = {ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
     pages = {7762--7766},
     year = {2022},
     organization = {IEEE},
   }

3. ICASSP

   

   Multi-stage and multi-loss training for fullband non-personalized and personalized speech enhancement

   Lianwu Chen, Chenglin Xu, Xu Zhang, Xinlei Ren, Xiguang Zheng, Chen Zhang, Liang Guo, and Bing Yu

   In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022

   Bib HTML

   @inproceedings{chen2022multi,
     title = {Multi-stage and multi-loss training for fullband non-personalized and personalized speech enhancement},
     author = {Chen, Lianwu and Xu, Chenglin and Zhang, Xu and Ren, Xinlei and Zheng, Xiguang and Zhang, Chen and Guo, Liang and Yu, Bing},
     booktitle = {ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
     pages = {9296--9300},
     year = {2022},
     organization = {IEEE},
   }

4. INTERSPEECH

   

   Impairment Representation Learning for Speech Quality Assessment

   Lianwu Chen, Xinlei Ren, Xu Zhang, Xiguang Zheng, Chen Zhang, Liang Guo, and Bing Yu

   In INTERSPEECH, 2022

   Bib PDF

   @inproceedings{chen2022impairment,
     title = {Impairment Representation Learning for Speech Quality Assessment},
     author = {Chen, Lianwu and Ren, Xinlei and Zhang, Xu and Zheng, Xiguang and Zhang, Chen and Guo, Liang and Yu, Bing},
     booktitle = {INTERSPEECH},
     pages = {3323--3327},
     year = {2022},
   }

2021

1. INTERSPEECH

   

   A Causal U-Net Based Neural Beamforming Network for Real-Time Multi-Channel Speech Enhancement

   Xinlei Ren, Xu Zhang, Lianwu Chen, Xiguang Zheng, Chen Zhang, Liang Guo, and Bing Yu

   In INTERSPEECH, 2021

   Bib PDF

   @inproceedings{ren2021causal,
     title = {A Causal U-Net Based Neural Beamforming Network for Real-Time Multi-Channel Speech Enhancement},
     author = {Ren, Xinlei and Zhang, Xu and Chen, Lianwu and Zheng, Xiguang and Zhang, Chen and Guo, Liang and Yu, Bing},
     booktitle = {INTERSPEECH},
     pages = {1832--1836},
     year = {2021},
   }

2. MLSP

   

   A neural beamforming network for b-format 3d speech enhancement and recognition

   Xinlei Ren, Lianwu Chen, Xiguang Zheng, Chenglin Xu, Xu Zhang, Chen Zhang, Liang Guo, and Bing Yu

   In 2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP), 2021

   Bib HTML

   @inproceedings{ren2021neural,
     title = {A neural beamforming network for b-format 3d speech enhancement and recognition},
     author = {Ren, Xinlei and Chen, Lianwu and Zheng, Xiguang and Xu, Chenglin and Zhang, Xu and Zhang, Chen and Guo, Liang and Yu, Bing},
     booktitle = {2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)},
     pages = {1--6},
     year = {2021},
     organization = {IEEE},
   }

3. INTERSPEECH

   

   Low-Delay Speech Enhancement Using Perceptually Motivated Target and Loss

   Xu Zhang, Xinlei Ren, Xiguang Zheng, Lianwu Chen, Chen Zhang, Liang Guo, and Bing Yu

   In INTERSPEECH, 2021

   Bib PDF

   @inproceedings{zhang2021low,
     title = {Low-Delay Speech Enhancement Using Perceptually Motivated Target and Loss},
     author = {Zhang, Xu and Ren, Xinlei and Zheng, Xiguang and Chen, Lianwu and Zhang, Chen and Guo, Liang and Yu, Bing},
     booktitle = {INTERSPEECH},
     pages = {2826--2830},
     year = {2021},
   }