Stop the war!
Остановите войну!
for scientists:
default search action
BibTeX records: Yong Xu 0004
@article{DBLP:journals/tmm/LiuXWW24, author = {Yang Liu and Yong Xu and Peipei Wu and Wenwu Wang}, title = {Labelled Non-Zero Diffusion Particle Flow {SMC-PHD} Filtering for Multi-Speaker Tracking}, journal = {{IEEE} Trans. Multim.}, volume = {26}, pages = {2544--2559}, year = {2024}, url = {https://doi.org/10.1109/TMM.2023.3301221}, doi = {10.1109/TMM.2023.3301221}, timestamp = {Thu, 29 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/tmm/LiuXWW24.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/YuXZZY23, author = {Meng Yu and Yong Xu and Chunlei Zhang and Shi{-}Xiong Zhang and Dong Yu}, title = {Neuralecho: Hybrid of Full-Band and Sub-Band Recurrent Neural Network For Acoustic Echo Cancellation and Speech Enhancement}, booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU} 2023, Taipei, Taiwan, December 16-20, 2023}, pages = {1--8}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ASRU57964.2023.10389728}, doi = {10.1109/ASRU57964.2023.10389728}, timestamp = {Tue, 13 Feb 2024 21:21:14 +0100}, biburl = {https://dblp.org/rec/conf/asru/YuXZZY23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/KothapallyXYZY23, author = {Vinay Kothapally and Yong Xu and Meng Yu and Shi{-}Xiong Zhang and Dong Yu}, title = {Deep Neural Mel-Subband Beamformer for in-Car Speech Separation}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023}, pages = {1--5}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICASSP49357.2023.10096974}, doi = {10.1109/ICASSP49357.2023.10096974}, timestamp = {Sun, 05 Nov 2023 16:51:21 +0100}, biburl = {https://dblp.org/rec/conf/icassp/KothapallyXYZY23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2309-07432, author = {Zhongweiyang Xu and Yong Xu and Vinay Kothapally and Heming Wang and Muqiao Yang and Dong Yu}, title = {SpatialCodec: Neural Spatial Speech Coding}, journal = {CoRR}, volume = {abs/2309.07432}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2309.07432}, doi = {10.48550/ARXIV.2309.07432}, eprinttype = {arXiv}, eprint = {2309.07432}, timestamp = {Tue, 19 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2309-07432.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eusipco/ZhaoWGLSXW22, author = {Jinzheng Zhao and Peipei Wu and Shidrokh Goudarzi and Xubo Liu and Jianyuan Sun and Yong Xu and Wenwu Wang}, title = {Visually Assisted Self-supervised Audio Speaker Localization and Tracking}, booktitle = {30th European Signal Processing Conference, {EUSIPCO} 2022, Belgrade, Serbia, August 29 - Sept. 2, 2022}, pages = {787--791}, publisher = {{IEEE}}, year = {2022}, url = {https://ieeexplore.ieee.org/document/9909535}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/eusipco/ZhaoWGLSXW22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/ZhaoWLXMGW22, author = {Jinzheng Zhao and Peipei Wu and Xubo Liu and Yong Xu and Lyudmila Mihaylova and Simon J. Godsill and Wenwu Wang}, title = {Audio-Visual Tracking of Multiple Speakers Via a {PMBM} Filter}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {5068--5072}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9747595}, doi = {10.1109/ICASSP43922.2022.9747595}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/ZhaoWLXMGW22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/Kothapally00Z022, author = {Vinay Kothapally and Yong Xu and Meng Yu and Shi{-}Xiong Zhang and Dong Yu}, editor = {Hanseok Ko and John H. L. Hansen}, title = {Joint Neural {AEC} and Beamforming with Double-Talk Detection}, booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022}, pages = {2528--2532}, publisher = {{ISCA}}, year = {2022}, url = {https://doi.org/10.21437/Interspeech.2022-10358}, doi = {10.21437/INTERSPEECH.2022-10358}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/Kothapally00Z022.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ZhaoWLGLXW22, author = {Jinzheng Zhao and Peipei Wu and Xubo Liu and Shidrokh Goudarzi and Haohe Liu and Yong Xu and Wenwu Wang}, editor = {Hanseok Ko and John H. L. Hansen}, title = {Audio Visual Multi-Speaker Tracking with Improved {GCF} and {PMBM} Filter}, booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022}, pages = {3704--3708}, publisher = {{ISCA}}, year = {2022}, url = {https://doi.org/10.21437/Interspeech.2022-10190}, doi = {10.21437/INTERSPEECH.2022-10190}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/ZhaoWLGLXW22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/MaitiUWZYZX22, author = {Soumi Maiti and Yushi Ueda and Shinji Watanabe and Chunlei Zhang and Meng Yu and Shi{-}Xiong Zhang and Yong Xu}, title = {{EEND-SS:} Joint End-to-End Neural Speaker Diarization and Speech Separation for Flexible Number of Speakers}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2022, Doha, Qatar, January 9-12, 2023}, pages = {480--487}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/SLT54892.2023.10022924}, doi = {10.1109/SLT54892.2023.10022924}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/MaitiUWZYZX22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-17068, author = {Yushi Ueda and Soumi Maiti and Shinji Watanabe and Chunlei Zhang and Meng Yu and Shi{-}Xiong Zhang and Yong Xu}, title = {{EEND-SS:} Joint End-to-End Neural Speaker Diarization and Speech Separation for Flexible Number of Speakers}, journal = {CoRR}, volume = {abs/2203.17068}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.17068}, doi = {10.48550/ARXIV.2203.17068}, eprinttype = {arXiv}, eprint = {2203.17068}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-17068.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2205-10401, author = {Meng Yu and Yong Xu and Chunlei Zhang and Shi{-}Xiong Zhang and Dong Yu}, title = {NeuralEcho: {A} Self-Attentive Recurrent Neural Network For Unified Acoustic Echo Suppression And Speech Enhancement}, journal = {CoRR}, volume = {abs/2205.10401}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2205.10401}, doi = {10.48550/ARXIV.2205.10401}, eprinttype = {arXiv}, eprint = {2205.10401}, timestamp = {Wed, 13 Jul 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2205-10401.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2211-12590, author = {Vinay Kothapally and Yong Xu and Meng Yu and Shi{-}Xiong Zhang and Dong Yu}, title = {Deep Neural Mel-Subband Beamformer for In-car Speech Separation}, journal = {CoRR}, volume = {abs/2211.12590}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2211.12590}, doi = {10.48550/ARXIV.2211.12590}, eprinttype = {arXiv}, eprint = {2211.12590}, timestamp = {Wed, 30 Nov 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2211-12590.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/MichelsantiTZXY21, author = {Daniel Michelsanti and Zheng{-}Hua Tan and Shi{-}Xiong Zhang and Yong Xu and Meng Yu and Dong Yu and Jesper Jensen}, title = {An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {29}, pages = {1368--1396}, year = {2021}, url = {https://doi.org/10.1109/TASLP.2021.3066303}, doi = {10.1109/TASLP.2021.3066303}, timestamp = {Thu, 29 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/MichelsantiTZXY21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/ZhangXYZCWY21, author = {Zhuohuang Zhang and Yong Xu and Meng Yu and Shi{-}Xiong Zhang and Lianwu Chen and Donald S. Williamson and Dong Yu}, title = {Multi-Channel Multi-Frame {ADL-MVDR} for Target Speech Separation}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {29}, pages = {3526--3540}, year = {2021}, url = {https://doi.org/10.1109/TASLP.2021.3129335}, doi = {10.1109/TASLP.2021.3129335}, timestamp = {Sat, 25 Dec 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/ZhangXYZCWY21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/Zhang00ZC021, author = {Zhuohuang Zhang and Yong Xu and Meng Yu and Shi{-}Xiong Zhang and Lianwu Chen and Dong Yu}, title = {{ADL-MVDR:} All Deep Learning {MVDR} Beamformer for Target Speech Separation}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021}, pages = {6089--6093}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICASSP39728.2021.9413594}, doi = {10.1109/ICASSP39728.2021.9413594}, timestamp = {Fri, 09 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/Zhang00ZC021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/SubramanianW00021, author = {Aswin Shanmugam Subramanian and Chao Weng and Shinji Watanabe and Meng Yu and Yong Xu and Shi{-}Xiong Zhang and Dong Yu}, title = {Directional {ASR:} {A} New Paradigm for {E2E} Multi-Speaker Speech Recognition with Source Localization}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021}, pages = {8433--8437}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICASSP39728.2021.9414243}, doi = {10.1109/ICASSP39728.2021.9414243}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/SubramanianW00021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/WangWC0YXZWSY21, author = {Helin Wang and Bo Wu and Lianwu Chen and Meng Yu and Jianwei Yu and Yong Xu and Shi{-}Xiong Zhang and Chao Weng and Dan Su and Dong Yu}, editor = {Hynek Hermansky and Honza Cernock{\'{y}} and Luk{\'{a}}s Burget and Lori Lamel and Odette Scharenborg and Petr Motl{\'{\i}}cek}, title = {TeCANet: Temporal-Contextual Attention Network for Environment-Aware Speech Dereverberation}, booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021}, pages = {1109--1113}, publisher = {{ISCA}}, year = {2021}, url = {https://doi.org/10.21437/Interspeech.2021-481}, doi = {10.21437/INTERSPEECH.2021-481}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/WangWC0YXZWSY21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiX0Z00021, author = {Xiyun Li and Yong Xu and Meng Yu and Shi{-}Xiong Zhang and Jiaming Xu and Bo Xu and Dong Yu}, editor = {Hynek Hermansky and Honza Cernock{\'{y}} and Luk{\'{a}}s Burget and Lori Lamel and Odette Scharenborg and Petr Motl{\'{\i}}cek}, title = {{MIMO} Self-Attentive {RNN} Beamformer for Multi-Speaker Speech Separation}, booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021}, pages = {1119--1123}, publisher = {{ISCA}}, year = {2021}, url = {https://doi.org/10.21437/Interspeech.2021-570}, doi = {10.21437/INTERSPEECH.2021-570}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LiX0Z00021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/YuZXZ021, author = {Meng Yu and Chunlei Zhang and Yong Xu and Shi{-}Xiong Zhang and Dong Yu}, editor = {Hynek Hermansky and Honza Cernock{\'{y}} and Luk{\'{a}}s Burget and Lori Lamel and Odette Scharenborg and Petr Motl{\'{\i}}cek}, title = {MetricNet: Towards Improved Modeling For Non-Intrusive Speech Quality Assessment}, booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021}, pages = {2142--2146}, publisher = {{ISCA}}, year = {2021}, url = {https://doi.org/10.21437/Interspeech.2021-659}, doi = {10.21437/INTERSPEECH.2021-659}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/YuZXZ021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XuZ0Z021, author = {Yong Xu and Zhuohuang Zhang and Meng Yu and Shi{-}Xiong Zhang and Dong Yu}, editor = {Hynek Hermansky and Honza Cernock{\'{y}} and Luk{\'{a}}s Burget and Lori Lamel and Odette Scharenborg and Petr Motl{\'{\i}}cek}, title = {Generalized Spatio-Temporal {RNN} Beamformer for Target Speech Separation}, booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021}, pages = {3076--3080}, publisher = {{ISCA}}, year = {2021}, url = {https://doi.org/10.21437/Interspeech.2021-430}, doi = {10.21437/INTERSPEECH.2021-430}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XuZ0Z021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/LiuYXWZC021, author = {Jianming Liu and Meng Yu and Yong Xu and Chao Weng and Shi{-}Xiong Zhang and Lianwu Chen and Dong Yu}, title = {Neural Mask based Multi-channel Convolutional Beamforming for Joint Dereverberation, Echo Cancellation and Denoising}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {766--770}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383519}, doi = {10.1109/SLT48900.2021.9383519}, timestamp = {Mon, 26 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/LiuYXWZC021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/NiXYWZYM21, author = {Zhaoheng Ni and Yong Xu and Meng Yu and Bo Wu and Shi{-}Xiong Zhang and Dong Yu and Michael I. Mandel}, title = {{WPD++:} An Improved Neural Beamformer for Simultaneous Speech Separation and Dereverberation}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {817--824}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383528}, doi = {10.1109/SLT48900.2021.9383528}, timestamp = {Fri, 23 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/NiXYWZYM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2101-01280, author = {Yong Xu and Zhuohuang Zhang and Meng Yu and Shi{-}Xiong Zhang and Lianwu Chen and Dong Yu}, title = {Generalized {RNN} beamformer for target speech separation}, journal = {CoRR}, volume = {abs/2101.01280}, year = {2021}, url = {https://arxiv.org/abs/2101.01280}, eprinttype = {arXiv}, eprint = {2101.01280}, timestamp = {Mon, 26 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2101-01280.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2103-16849, author = {Helin Wang and Bo Wu and Lianwu Chen and Meng Yu and Jianwei Yu and Yong Xu and Shi{-}Xiong Zhang and Chao Weng and Dan Su and Dong Yu}, title = {TeCANet: Temporal-Contextual Attention Network for Environment-Aware Speech Dereverberation}, journal = {CoRR}, volume = {abs/2103.16849}, year = {2021}, url = {https://arxiv.org/abs/2103.16849}, eprinttype = {arXiv}, eprint = {2103.16849}, timestamp = {Tue, 07 Dec 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2103-16849.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2104-01227, author = {Meng Yu and Chunlei Zhang and Yong Xu and Shi{-}Xiong Zhang and Dong Yu}, title = {MetricNet: Towards Improved Modeling For Non-Intrusive Speech Quality Assessment}, journal = {CoRR}, volume = {abs/2104.01227}, year = {2021}, url = {https://arxiv.org/abs/2104.01227}, eprinttype = {arXiv}, eprint = {2104.01227}, timestamp = {Fri, 23 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2104-01227.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2104-08450, author = {Xiyun Li and Yong Xu and Meng Yu and Shi{-}Xiong Zhang and Jiaming Xu and Bo Xu and Dong Yu}, title = {{MIMO} Self-attentive {RNN} Beamformer for Multi-speaker Speech Separation}, journal = {CoRR}, volume = {abs/2104.08450}, year = {2021}, url = {https://arxiv.org/abs/2104.08450}, eprinttype = {arXiv}, eprint = {2104.08450}, timestamp = {Tue, 14 Dec 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2104-08450.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2111-04904, author = {Vinay Kothapally and Yong Xu and Meng Yu and Shi{-}Xiong Zhang and Dong Yu}, title = {Joint {AEC} {AND} Beamforming with Double-Talk Detection using RNN-Transformer}, journal = {CoRR}, volume = {abs/2111.04904}, year = {2021}, url = {https://arxiv.org/abs/2111.04904}, eprinttype = {arXiv}, eprint = {2111.04904}, timestamp = {Tue, 14 Dec 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2111-04904.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jstsp/GuZXCZY20, author = {Rongzhi Gu and Shi{-}Xiong Zhang and Yong Xu and Lianwu Chen and Yuexian Zou and Dong Yu}, title = {Multi-Modal Multi-Channel Target Speech Separation}, journal = {{IEEE} J. Sel. Top. Signal Process.}, volume = {14}, number = {3}, pages = {530--541}, year = {2020}, url = {https://doi.org/10.1109/JSTSP.2020.2980956}, doi = {10.1109/JSTSP.2020.2980956}, timestamp = {Thu, 06 Aug 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jstsp/GuZXCZY20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jstsp/TanXZYY20, author = {Ke Tan and Yong Xu and Shi{-}Xiong Zhang and Meng Yu and Dong Yu}, title = {Audio-Visual Speech Separation and Dereverberation With a Two-Stage Multimodal Network}, journal = {{IEEE} J. Sel. Top. Signal Process.}, volume = {14}, number = {3}, pages = {542--553}, year = {2020}, url = {https://doi.org/10.1109/JSTSP.2020.2987209}, doi = {10.1109/JSTSP.2020.2987209}, timestamp = {Tue, 15 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/jstsp/TanXZYY20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/KongXWP20, author = {Qiuqiang Kong and Yong Xu and Wenwu Wang and Mark D. Plumbley}, title = {Sound Event Detection of Weakly Labelled Data With CNN-Transformer and Automatic Threshold Optimization}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {28}, pages = {2450--2460}, year = {2020}, url = {https://doi.org/10.1109/TASLP.2020.3014737}, doi = {10.1109/TASLP.2020.3014737}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/KongXWP20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/DingXZCW20, author = {Yifan Ding and Yong Xu and Shi{-}Xiong Zhang and Yahuan Cong and Liqiang Wang}, title = {Self-Supervised Learning for Audio-Visual Speaker Diarization}, booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020}, pages = {4367--4371}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ICASSP40776.2020.9054376}, doi = {10.1109/ICASSP40776.2020.9054376}, timestamp = {Tue, 29 Nov 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/DingXZCW20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/SubramanianWYZX20, author = {Aswin Shanmugam Subramanian and Chao Weng and Meng Yu and Shi{-}Xiong Zhang and Yong Xu and Shinji Watanabe and Dong Yu}, title = {Far-Field Location Guided Target Speech Extraction Using End-to-End Speech Recognition Objectives}, booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020}, pages = {7299--7303}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ICASSP40776.2020.9053692}, doi = {10.1109/ICASSP40776.2020.9053692}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/SubramanianWYZX20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/GuZCXYSZY20, author = {Rongzhi Gu and Shi{-}Xiong Zhang and Lianwu Chen and Yong Xu and Meng Yu and Dan Su and Yuexian Zou and Dong Yu}, title = {Enhancing End-to-End Multi-Channel Speech Separation Via Spatial Feature Learning}, booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020}, pages = {7319--7323}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ICASSP40776.2020.9053092}, doi = {10.1109/ICASSP40776.2020.9053092}, timestamp = {Fri, 30 Oct 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/GuZCXYSZY20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XuYZCWL020, author = {Yong Xu and Meng Yu and Shi{-}Xiong Zhang and Lianwu Chen and Chao Weng and Jianming Liu and Dong Yu}, editor = {Helen Meng and Bo Xu and Thomas Fang Zheng}, title = {Neural Spatio-Temporal Beamformer for Target Speech Separation}, booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020}, pages = {56--60}, publisher = {{ISCA}}, year = {2020}, url = {https://doi.org/10.21437/Interspeech.2020-1458}, doi = {10.21437/INTERSPEECH.2020-1458}, timestamp = {Fri, 05 Feb 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/XuYZCWL020.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/YuWGZCX00YLM20, author = {Jianwei Yu and Bo Wu and Rongzhi Gu and Shi{-}Xiong Zhang and Lianwu Chen and Yong Xu and Meng Yu and Dan Su and Dong Yu and Xunying Liu and Helen Meng}, editor = {Helen Meng and Bo Xu and Thomas Fang Zheng}, title = {Audio-Visual Multi-Channel Recognition of Overlapped Speech}, booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020}, pages = {3496--3500}, publisher = {{ISCA}}, year = {2020}, url = {https://doi.org/10.21437/Interspeech.2020-2346}, doi = {10.21437/INTERSPEECH.2020-2346}, timestamp = {Fri, 05 Feb 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/YuWGZCX00YLM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2002-05314, author = {Yifan Ding and Yong Xu and Shi{-}Xiong Zhang and Yahuan Cong and Liqiang Wang}, title = {Self-supervised learning for audio-visual speaker diarization}, journal = {CoRR}, volume = {abs/2002.05314}, year = {2020}, url = {https://arxiv.org/abs/2002.05314}, eprinttype = {arXiv}, eprint = {2002.05314}, timestamp = {Tue, 29 Nov 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2002-05314.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2003-03927, author = {Rongzhi Gu and Shi{-}Xiong Zhang and Lianwu Chen and Yong Xu and Meng Yu and Dan Su and Yuexian Zou and Dong Yu}, title = {Enhancing End-to-End Multi-channel Speech Separation via Spatial Feature Learning}, journal = {CoRR}, volume = {abs/2003.03927}, year = {2020}, url = {https://arxiv.org/abs/2003.03927}, eprinttype = {arXiv}, eprint = {2003.03927}, timestamp = {Sat, 29 Aug 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2003-03927.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2003-07032, author = {Rongzhi Gu and Shi{-}Xiong Zhang and Yong Xu and Lianwu Chen and Yuexian Zou and Dong Yu}, title = {Multi-modal Multi-channel Target Speech Separation}, journal = {CoRR}, volume = {abs/2003.07032}, year = {2020}, url = {https://arxiv.org/abs/2003.07032}, eprinttype = {arXiv}, eprint = {2003.07032}, timestamp = {Tue, 14 Jul 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2003-07032.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2005-03889, author = {Yong Xu and Meng Yu and Shi{-}Xiong Zhang and Lianwu Chen and Chao Weng and Jianming Liu and Dong Yu}, title = {Neural Spatio-Temporal Beamformer for Target Speech Separation}, journal = {CoRR}, volume = {abs/2005.03889}, year = {2020}, url = {https://arxiv.org/abs/2005.03889}, eprinttype = {arXiv}, eprint = {2005.03889}, timestamp = {Thu, 06 Aug 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2005-03889.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2005-08571, author = {Jianwei Yu and Bo Wu and Rongzhi Gu and Shi{-}Xiong Zhang and Lianwu Chen and Yong Xu and Meng Yu and Dan Su and Dong Yu and Xunying Liu and Helen Meng}, title = {Audio-visual Multi-channel Recognition of Overlapped Speech}, journal = {CoRR}, volume = {abs/2005.08571}, year = {2020}, url = {https://arxiv.org/abs/2005.08571}, eprinttype = {arXiv}, eprint = {2005.08571}, timestamp = {Fri, 30 Oct 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2005-08571.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2008-09586, author = {Daniel Michelsanti and Zheng{-}Hua Tan and Shi{-}Xiong Zhang and Yong Xu and Meng Yu and Dong Yu and Jesper Jensen}, title = {An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation}, journal = {CoRR}, volume = {abs/2008.09586}, year = {2020}, url = {https://arxiv.org/abs/2008.09586}, eprinttype = {arXiv}, eprint = {2008.09586}, timestamp = {Fri, 05 Feb 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2008-09586.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2011-00091, author = {Aswin Shanmugam Subramanian and Chao Weng and Shinji Watanabe and Meng Yu and Yong Xu and Shi{-}Xiong Zhang and Dong Yu}, title = {Directional {ASR:} {A} New Paradigm for {E2E} Multi-Speaker Speech Recognition with Source Localization}, journal = {CoRR}, volume = {abs/2011.00091}, year = {2020}, url = {https://arxiv.org/abs/2011.00091}, eprinttype = {arXiv}, eprint = {2011.00091}, timestamp = {Fri, 05 Feb 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2011-00091.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2011-09162, author = {Zhaoheng Ni and Yong Xu and Meng Yu and Bo Wu and Shi{-}Xiong Zhang and Dong Yu and Michael I. Mandel}, title = {{WPD++:} An Improved Neural Beamformer for Simultaneous Speech Separation and Dereverberation}, journal = {CoRR}, volume = {abs/2011.09162}, year = {2020}, url = {https://arxiv.org/abs/2011.09162}, eprinttype = {arXiv}, eprint = {2011.09162}, timestamp = {Fri, 23 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2011-09162.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2012-13442, author = {Zhuohuang Zhang and Yong Xu and Meng Yu and Shi{-}Xiong Zhang and Lianwu Chen and Donald S. Williamson and Dong Yu}, title = {Multi-channel Multi-frame {ADL-MVDR} for Target Speech Separation}, journal = {CoRR}, volume = {abs/2012.13442}, year = {2020}, url = {https://arxiv.org/abs/2012.13442}, eprinttype = {arXiv}, eprint = {2012.13442}, timestamp = {Fri, 23 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2012-13442.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/KongXSWP19, author = {Qiuqiang Kong and Yong Xu and Iwona Sobieraj and Wenwu Wang and Mark D. Plumbley}, title = {Sound Event Detection and Time-Frequency Segmentation from Weakly Labelled Data}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {27}, number = {4}, pages = {777--787}, year = {2019}, url = {https://doi.org/10.1109/TASLP.2019.2895254}, doi = {10.1109/TASLP.2019.2895254}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/KongXSWP19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/KongYXIWP19, author = {Qiuqiang Kong and Changsong Yu and Yong Xu and Turab Iqbal and Wenwu Wang and Mark D. Plumbley}, title = {Weakly Labelled AudioSet Tagging With Attention Neural Networks}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {27}, number = {11}, pages = {1791--1802}, year = {2019}, url = {https://doi.org/10.1109/TASLP.2019.2930913}, doi = {10.1109/TASLP.2019.2930913}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/KongYXIWP19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/WuXZCYXY19, author = {Jian Wu and Yong Xu and Shi{-}Xiong Zhang and Lianwu Chen and Meng Yu and Lei Xie and Dong Yu}, title = {Time Domain Audio Visual Speech Separation}, booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU} 2019, Singapore, December 14-18, 2019}, pages = {667--673}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ASRU46091.2019.9003983}, doi = {10.1109/ASRU46091.2019.9003983}, timestamp = {Thu, 11 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/asru/WuXZCYXY19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/KongXICWP19, author = {Qiuqiang Kong and Yong Xu and Turab Iqbal and Yin Cao and Wenwu Wang and Mark D. Plumbley}, title = {Acoustic Scene Generation with Conditional Samplernn}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019}, pages = {925--929}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ICASSP.2019.8683727}, doi = {10.1109/ICASSP.2019.8683727}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/KongXICWP19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XuWHLYSY19, author = {Yong Xu and Chao Weng and Like Hui and Jianming Liu and Meng Yu and Dan Su and Dong Yu}, title = {Joint Training of Complex Ratio Mask Based Beamformer and Acoustic Model for Noise Robust Asr}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019}, pages = {6745--6749}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ICASSP.2019.8682576}, doi = {10.1109/ICASSP.2019.8682576}, timestamp = {Fri, 05 Feb 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/XuWHLYSY19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcai/KongXJWP19, author = {Qiuqiang Kong and Yong Xu and Philip J. B. Jackson and Wenwu Wang and Mark D. Plumbley}, editor = {Sarit Kraus}, title = {Single-Channel Signal Separation and Deconvolution with Generative Adversarial Networks}, booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, {IJCAI} 2019, Macao, China, August 10-16, 2019}, pages = {2747--2753}, publisher = {ijcai.org}, year = {2019}, url = {https://doi.org/10.24963/ijcai.2019/381}, doi = {10.24963/IJCAI.2019/381}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ijcai/KongXJWP19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/WuXZCYX019, author = {Jian Wu and Yong Xu and Shi{-}Xiong Zhang and Lianwu Chen and Meng Yu and Lei Xie and Dong Yu}, editor = {Gernot Kubin and Zdravko Kacic}, title = {Improved Speaker-Dependent Separation for CHiME-5 Challenge}, booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019}, pages = {466--470}, publisher = {{ISCA}}, year = {2019}, url = {https://doi.org/10.21437/Interspeech.2019-1569}, doi = {10.21437/INTERSPEECH.2019-1569}, timestamp = {Thu, 11 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/WuXZCYX019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/GuCZZXYSZ019, author = {Rongzhi Gu and Lianwu Chen and Shi{-}Xiong Zhang and Jimeng Zheng and Yong Xu and Meng Yu and Dan Su and Yuexian Zou and Dong Yu}, editor = {Gernot Kubin and Zdravko Kacic}, title = {Neural Spatial Filter: Target Speaker Speech Separation Assisted with Directional Information}, booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019}, pages = {4290--4294}, publisher = {{ISCA}}, year = {2019}, url = {https://doi.org/10.21437/Interspeech.2019-2266}, doi = {10.21437/INTERSPEECH.2019-2266}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/GuCZZXYSZ019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/BahmaninezhadWG19, author = {Fahimeh Bahmaninezhad and Jian Wu and Rongzhi Gu and Shi{-}Xiong Zhang and Yong Xu and Meng Yu and Dong Yu}, editor = {Gernot Kubin and Zdravko Kacic}, title = {A Comprehensive Study of Speech Separation: Spectrogram vs Waveform Separation}, booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019}, pages = {4574--4578}, publisher = {{ISCA}}, year = {2019}, url = {https://doi.org/10.21437/Interspeech.2019-3181}, doi = {10.21437/INTERSPEECH.2019-3181}, timestamp = {Tue, 17 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/BahmaninezhadWG19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1903-00765, author = {Qiuqiang Kong and Changsong Yu and Turab Iqbal and Yong Xu and Wenwu Wang and Mark D. Plumbley}, title = {Weakly labelled AudioSet Classification with Attention Neural Networks}, journal = {CoRR}, volume = {abs/1903.00765}, year = {2019}, url = {http://arxiv.org/abs/1903.00765}, eprinttype = {arXiv}, eprint = {1903.00765}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1903-00765.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1904-03476, author = {Qiuqiang Kong and Yin Cao and Turab Iqbal and Yong Xu and Wenwu Wang and Mark D. Plumbley}, title = {Cross-task learning for audio tagging, sound event detection and spatial localization: {DCASE} 2019 baseline systems}, journal = {CoRR}, volume = {abs/1904.03476}, year = {2019}, url = {http://arxiv.org/abs/1904.03476}, eprinttype = {arXiv}, eprint = {1904.03476}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1904-03476.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1904-03760, author = {Jian Wu and Yong Xu and Shi{-}Xiong Zhang and Lianwu Chen and Meng Yu and Lei Xie and Dong Yu}, title = {Time Domain Audio Visual Speech Separation}, journal = {CoRR}, volume = {abs/1904.03760}, year = {2019}, url = {http://arxiv.org/abs/1904.03760}, eprinttype = {arXiv}, eprint = {1904.03760}, timestamp = {Thu, 11 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1904-03760.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1904-03792, author = {Jian Wu and Yong Xu and Shi{-}Xiong Zhang and Lianwu Chen and Meng Yu and Lei Xie and Dong Yu}, title = {Improved Speaker-Dependent Separation for CHiME-5 Challenge}, journal = {CoRR}, volume = {abs/1904.03792}, year = {2019}, url = {http://arxiv.org/abs/1904.03792}, eprinttype = {arXiv}, eprint = {1904.03792}, timestamp = {Thu, 11 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1904-03792.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1905-06286, author = {Rongzhi Gu and Jian Wu and Shi{-}Xiong Zhang and Lianwu Chen and Yong Xu and Meng Yu and Dan Su and Yuexian Zou and Dong Yu}, title = {End-to-End Multi-Channel Speech Separation}, journal = {CoRR}, volume = {abs/1905.06286}, year = {2019}, url = {http://arxiv.org/abs/1905.06286}, eprinttype = {arXiv}, eprint = {1905.06286}, timestamp = {Tue, 17 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1905-06286.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1905-07497, author = {Fahimeh Bahmaninezhad and Jian Wu and Rongzhi Gu and Shi{-}Xiong Zhang and Yong Xu and Meng Yu and Dong Yu}, title = {A comprehensive study of speech separation: spectrogram vs waveform separation}, journal = {CoRR}, volume = {abs/1905.07497}, year = {2019}, url = {http://arxiv.org/abs/1905.07497}, eprinttype = {arXiv}, eprint = {1905.07497}, timestamp = {Tue, 17 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1905-07497.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1906-07552, author = {Qiuqiang Kong and Yong Xu and Wenwu Wang and Philip J. B. Jackson and Mark D. Plumbley}, title = {Single-Channel Signal Separation and Deconvolution with Generative Adversarial Networks}, journal = {CoRR}, volume = {abs/1906.07552}, year = {2019}, url = {http://arxiv.org/abs/1906.07552}, eprinttype = {arXiv}, eprint = {1906.07552}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1906-07552.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1909-07352, author = {Ke Tan and Yong Xu and Shi{-}Xiong Zhang and Meng Yu and Dong Yu}, title = {Audio-Visual Speech Separation and Dereverberation with a Two-Stage Multimodal Network}, journal = {CoRR}, volume = {abs/1909.07352}, year = {2019}, url = {http://arxiv.org/abs/1909.07352}, eprinttype = {arXiv}, eprint = {1909.07352}, timestamp = {Tue, 15 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1909-07352.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1912-04761, author = {Qiuqiang Kong and Yong Xu and Wenwu Wang and Mark D. Plumbley}, title = {Sound Event Detection of Weakly Labelled Data with CNN-Transformer and Automatic Threshold Optimization}, journal = {CoRR}, volume = {abs/1912.04761}, year = {2019}, url = {http://arxiv.org/abs/1912.04761}, eprinttype = {arXiv}, eprint = {1912.04761}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1912-04761.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1912-07814, author = {Fahimeh Bahmaninezhad and Shi{-}Xiong Zhang and Yong Xu and Meng Yu and John H. L. Hansen and Dong Yu}, title = {A Unified Framework for Speech Separation}, journal = {CoRR}, volume = {abs/1912.07814}, year = {2019}, url = {http://arxiv.org/abs/1912.07814}, eprinttype = {arXiv}, eprint = {1912.07814}, timestamp = {Fri, 05 Feb 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1912-07814.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/vlsisp/SunDXX18, author = {Lei Sun and Jun Du and Zhipeng Xie and Yong Xu}, title = {Auxiliary Features from Laser-Doppler Vibrometer Sensor for Deep Neural Network Based Robust Speech Recognition}, journal = {J. Signal Process. Syst.}, volume = {90}, number = {7}, pages = {975--983}, year = {2018}, url = {https://doi.org/10.1007/s11265-017-1287-x}, doi = {10.1007/S11265-017-1287-X}, timestamp = {Sun, 31 Dec 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/vlsisp/SunDXX18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/dcase/KongIXWP18, author = {Qiuqiang Kong and Turab Iqbal and Yong Xu and Wenwu Wang and Mark D. Plumbley}, editor = {Mark D. Plumbley and Christian Kroos and Juan Pablo Bello and Ga{\"{e}}l Richard and Daniel P. W. Ellis and Annamaria Mesaros}, title = {{DCASE} 2018 Challenge Surrey cross-task convolutional neural network baseline}, booktitle = {Proceedings of the Workshop on Detection and Classification of Acoustic Scenes and Events, {DCASE} 2018, Surrey, UK, November 19-20, 2018}, pages = {217--221}, year = {2018}, url = {http://dcase.community/documents/workshop2018/proceedings/DCASE2018Workshop\_Kong\_152.pdf}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/dcase/KongIXWP18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eusipco/Iqbal0KW18, author = {Turab Iqbal and Yong Xu and Qiuqiang Kong and Wenwu Wang}, title = {Capsule Routing for Sound Event Detection}, booktitle = {26th European Signal Processing Conference, {EUSIPCO} 2018, Roma, Italy, September 3-7, 2018}, pages = {2255--2259}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.23919/EUSIPCO.2018.8553198}, doi = {10.23919/EUSIPCO.2018.8553198}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/eusipco/Iqbal0KW18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/hci/DuelFK0JP18, author = {Tijs Duel and David M. Frohlich and Christian Kroos and Yong Xu and Philip J. B. Jackson and Mark D. Plumbley}, editor = {Constantine Stephanidis}, title = {Supporting Audiography: Design of a System for Sentimental Sound Recording, Classification and Playback}, booktitle = {{HCI} International 2018 - Posters' Extended Abstracts, 20th International Conference, {HCI} International 2018, Las Vegas, NV, USA, July 15-20, 2018, Proceedings, Part {I}}, series = {Communications in Computer and Information Science}, volume = {850}, pages = {24--31}, publisher = {Springer}, year = {2018}, url = {https://doi.org/10.1007/978-3-319-92270-6\_4}, doi = {10.1007/978-3-319-92270-6\_4}, timestamp = {Tue, 12 Sep 2023 07:57:19 +0200}, biburl = {https://dblp.org/rec/conf/hci/DuelFK0JP18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ica/ZerminiKXPW18, author = {Alfredo Zermini and Qiuqiang Kong and Yong Xu and Mark D. Plumbley and Wenwu Wang}, editor = {Yannick Deville and Sharon Gannot and Russell Mason and Mark D. Plumbley and Dominic Ward}, title = {Improving Reverberant Speech Separation with Binaural Cues Using Temporal Context and Convolutional Neural Networks}, booktitle = {Latent Variable Analysis and Signal Separation - 14th International Conference, {LVA/ICA} 2018, Guildford, UK, July 2-5, 2018, Proceedings}, series = {Lecture Notes in Computer Science}, volume = {10891}, pages = {361--371}, publisher = {Springer}, year = {2018}, url = {https://doi.org/10.1007/978-3-319-93764-9\_34}, doi = {10.1007/978-3-319-93764-9\_34}, timestamp = {Mon, 26 Jun 2023 20:48:01 +0200}, biburl = {https://dblp.org/rec/conf/ica/ZerminiKXPW18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/0004KWP18, author = {Yong Xu and Qiuqiang Kong and Wenwu Wang and Mark D. Plumbley}, title = {Large-Scale Weakly Supervised Audio Classification Using Gated Convolutional Neural Network}, booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018}, pages = {121--125}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/ICASSP.2018.8461975}, doi = {10.1109/ICASSP.2018.8461975}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/0004KWP18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/Kong0WP18, author = {Qiuqiang Kong and Yong Xu and Wenwu Wang and Mark D. Plumbley}, title = {Audio Set Classification with Attention Model: {A} Probabilistic Perspective}, booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018}, pages = {316--320}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/ICASSP.2018.8461392}, doi = {10.1109/ICASSP.2018.8461392}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/Kong0WP18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/KongXWP18, author = {Qiuqiang Kong and Yong Xu and Wenwu Wang and Mark D. Plumbley}, title = {A Joint Separation-Classification Model for Sound Event Detection of Weakly Labelled Data}, booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018}, pages = {321--325}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/ICASSP.2018.8462448}, doi = {10.1109/ICASSP.2018.8462448}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/KongXWP18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/Liu0JWC18, author = {Qingju Liu and Yong Xu and Philip J. B. Jackson and Wenwu Wang and Philip Coleman}, title = {Iterative Deep Neural Networks for Speaker-Independent Binaural Blind Speech Separation}, booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018}, pages = {541--545}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/ICASSP.2018.8462603}, doi = {10.1109/ICASSP.2018.8462603}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/Liu0JWC18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1804-04715, author = {Qiuqiang Kong and Yong Xu and Iwona Sobieraj and Wenwu Wang and Mark D. Plumbley}, title = {Sound Event Detection and Time-Frequency Segmentation from Weakly Labelled Data}, journal = {CoRR}, volume = {abs/1804.04715}, year = {2018}, url = {http://arxiv.org/abs/1804.04715}, eprinttype = {arXiv}, eprint = {1804.04715}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1804-04715.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1806-04699, author = {Turab Iqbal and Yong Xu and Qiuqiang Kong and Wenwu Wang}, title = {Capsule Routing for Sound Event Detection}, journal = {CoRR}, volume = {abs/1806.04699}, year = {2018}, url = {http://arxiv.org/abs/1806.04699}, eprinttype = {arXiv}, eprint = {1806.04699}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1806-04699.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1808-00773, author = {Qiuqiang Kong and Turab Iqbal and Yong Xu and Wenwu Wang and Mark D. Plumbley}, title = {{DCASE} 2018 Challenge baseline with convolutional neural networks}, journal = {CoRR}, volume = {abs/1808.00773}, year = {2018}, url = {http://arxiv.org/abs/1808.00773}, eprinttype = {arXiv}, eprint = {1808.00773}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1808-00773.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/pr/DuX17, author = {Jun Du and Yong Xu}, title = {Hierarchical deep neural network for multivariate regression}, journal = {Pattern Recognit.}, volume = {63}, pages = {149--157}, year = {2017}, url = {https://doi.org/10.1016/j.patcog.2016.10.003}, doi = {10.1016/J.PATCOG.2016.10.003}, timestamp = {Mon, 24 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/pr/DuX17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/XuHWFSJP17, author = {Yong Xu and Qiang Huang and Wenwu Wang and Peter Foster and Siddharth Sigtia and Philip J. B. Jackson and Mark D. Plumbley}, title = {Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {25}, number = {6}, pages = {1230--1241}, year = {2017}, url = {https://doi.org/10.1109/TASLP.2017.2690563}, doi = {10.1109/TASLP.2017.2690563}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/XuHWFSJP17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/eusipco/KongXP17, author = {Qiuqiang Kong and Yong Xu and Mark D. Plumbley}, title = {Joint detection and classification convolutional neural network on weakly labelled bird audio detection}, booktitle = {25th European Signal Processing Conference, {EUSIPCO} 2017, Kos, Greece, August 28 - September 2, 2017}, pages = {1749--1753}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.23919/EUSIPCO.2017.8081509}, doi = {10.23919/EUSIPCO.2017.8081509}, timestamp = {Wed, 16 Oct 2019 14:14:50 +0200}, biburl = {https://dblp.org/rec/conf/eusipco/KongXP17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/KongXWP17, author = {Qiuqiang Kong and Yong Xu and Wenwu Wang and Mark D. Plumbley}, title = {A joint detection-classification model for audio tagging of weakly labelled data}, booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017}, pages = {641--645}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/ICASSP.2017.7952234}, doi = {10.1109/ICASSP.2017.7952234}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/KongXWP17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/HuangXJWP17, author = {Qiang Huang and Yong Xu and Philip J. B. Jackson and Wenwu Wang and Mark D. Plumbley}, title = {Fast tagging of natural sounds using marginal co-regularization}, booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017}, pages = {2991--2995}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/ICASSP.2017.7952705}, doi = {10.1109/ICASSP.2017.7952705}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/HuangXJWP17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcnn/XuKHWP17, author = {Yong Xu and Qiuqiang Kong and Qiang Huang and Wenwu Wang and Mark D. Plumbley}, title = {Convolutional gated recurrent neural network incorporating spatial features for audio tagging}, booktitle = {2017 International Joint Conference on Neural Networks, {IJCNN} 2017, Anchorage, AK, USA, May 14-19, 2017}, pages = {3461--3466}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/IJCNN.2017.7966291}, doi = {10.1109/IJCNN.2017.7966291}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ijcnn/XuKHWP17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XuKHWP17, author = {Yong Xu and Qiuqiang Kong and Qiang Huang and Wenwu Wang and Mark D. Plumbley}, editor = {Francisco Lacerda}, title = {Attention and Localization Based on a Deep Convolutional Recurrent Model for Weakly Supervised Audio Tagging}, booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017}, pages = {3083--3087}, publisher = {{ISCA}}, year = {2017}, url = {https://doi.org/10.21437/Interspeech.2017-486}, doi = {10.21437/INTERSPEECH.2017-486}, timestamp = {Sun, 06 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XuKHWP17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/mmsp/ZerminiLXPBW17, author = {Alfredo Zermini and Qingju Liu and Yong Xu and Mark D. Plumbley and Dave Betts and Wenwu Wang}, title = {Binaural and log-power spectra features with deep neural networks for speech-noise separation}, booktitle = {19th {IEEE} International Workshop on Multimedia Signal Processing, {MMSP} 2017, Luton, United Kingdom, October 16-18, 2017}, pages = {1--6}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/MMSP.2017.8122280}, doi = {10.1109/MMSP.2017.8122280}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/mmsp/ZerminiLXPBW17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/XuKHWP17, author = {Yong Xu and Qiuqiang Kong and Qiang Huang and Wenwu Wang and Mark D. Plumbley}, title = {Convolutional Gated Recurrent Neural Network Incorporating Spatial Features for Audio Tagging}, journal = {CoRR}, volume = {abs/1702.07787}, year = {2017}, url = {http://arxiv.org/abs/1702.07787}, eprinttype = {arXiv}, eprint = {1702.07787}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/XuKHWP17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/XuKHWP17a, author = {Yong Xu and Qiuqiang Kong and Qiang Huang and Wenwu Wang and Mark D. Plumbley}, title = {Attention and Localization based on a Deep Convolutional Recurrent Model for Weakly Supervised Audio Tagging}, journal = {CoRR}, volume = {abs/1703.06052}, year = {2017}, url = {http://arxiv.org/abs/1703.06052}, eprinttype = {arXiv}, eprint = {1703.06052}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/XuKHWP17a.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/XuDHDL17, author = {Yong Xu and Jun Du and Zhen Huang and Li{-}Rong Dai and Chin{-}Hui Lee}, title = {Multi-Objective Learning and Mask-Based Post-Processing for Deep Neural Network Based Speech Enhancement}, journal = {CoRR}, volume = {abs/1703.07172}, year = {2017}, url = {http://arxiv.org/abs/1703.07172}, eprinttype = {arXiv}, eprint = {1703.07172}, timestamp = {Thu, 14 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/XuDHDL17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1709-00551, author = {Yong Xu and Qiuqiang Kong and Wenwu Wang and Mark D. Plumbley}, title = {Surrey-cvssp system for {DCASE2017} challenge task4}, journal = {CoRR}, volume = {abs/1709.00551}, year = {2017}, url = {http://arxiv.org/abs/1709.00551}, eprinttype = {arXiv}, eprint = {1709.00551}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1709-00551.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1710-00343, author = {Yong Xu and Qiuqiang Kong and Wenwu Wang and Mark D. Plumbley}, title = {Large-scale weakly supervised audio classification using gated convolutional neural network}, journal = {CoRR}, volume = {abs/1710.00343}, year = {2017}, url = {http://arxiv.org/abs/1710.00343}, eprinttype = {arXiv}, eprint = {1710.00343}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1710-00343.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1711-00927, author = {Qiuqiang Kong and Yong Xu and Wenwu Wang and Mark D. Plumbley}, title = {Audio Set classification with attention model: {A} probabilistic perspective}, journal = {CoRR}, volume = {abs/1711.00927}, year = {2017}, url = {http://arxiv.org/abs/1711.00927}, eprinttype = {arXiv}, eprint = {1711.00927}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1711-00927.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1711-03037, author = {Qiuqiang Kong and Yong Xu and Wenwu Wang and Mark D. Plumbley}, title = {A joint separation-classification model for sound event detection of weakly labelled data}, journal = {CoRR}, volume = {abs/1711.03037}, year = {2017}, url = {http://arxiv.org/abs/1711.03037}, eprinttype = {arXiv}, eprint = {1711.03037}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1711-03037.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ejasp/GaoDXLDL16, author = {Tian Gao and Jun Du and Yong Xu and Cong Liu and Li{-}Rong Dai and Chin{-}Hui Lee}, title = {Joint training of DNNs by incorporating an explicit dereverberation structure for distant speech recognition}, journal = {{EURASIP} J. Adv. Signal Process.}, volume = {2016}, pages = {86}, year = {2016}, url = {https://doi.org/10.1186/s13634-016-0384-5}, doi = {10.1186/S13634-016-0384-5}, timestamp = {Thu, 14 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ejasp/GaoDXLDL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/dcase/XuHWJP16, author = {Yong Xu and Qiang Huang and Wenwu Wang and Philip J. B. Jackson and Mark D. Plumbley}, editor = {Tuomas Virtanen and Annamaria Mesaros and Toni Heittola and Mark D. Plumbley and Peter Foster and Emmanouil Benetos and Mathieu Lagrange}, title = {Fully DNN-Based Multi-Label Regression for Audio Tagging}, booktitle = {Proceedings of the Workshop on Detection and Classification of Acoustic Scenes and Events, {DCASE} 2016, Budapest, Hungary, September 3, 2016}, pages = {105--109}, year = {2016}, url = {http://dcase.community/documents/workshop2016/proceedings/Xu-b-DCASE2016workshop.pdf}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/dcase/XuHWJP16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/dcase/XuHWP16, author = {Yong Xu and Qiang Huang and Wenwu Wang and Mark D. Plumbley}, editor = {Tuomas Virtanen and Annamaria Mesaros and Toni Heittola and Mark D. Plumbley and Peter Foster and Emmanouil Benetos and Mathieu Lagrange}, title = {Hierarchical Learning for DNN-Based Acoustic Scene Classification}, booktitle = {Proceedings of the Workshop on Detection and Classification of Acoustic Scenes and Events, {DCASE} 2016, Budapest, Hungary, September 3, 2016}, pages = {110--114}, year = {2016}, url = {http://dcase.community/documents/workshop2016/proceedings/Xu-a-DCASE2016workshop.pdf}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/dcase/XuHWP16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/XieDMXMW16, author = {Zhipeng Xie and Jun Du and Ian McLoughlin and Yong Xu and Feng Ma and Haikun Wang}, title = {Deep neural network for robust speech recognition with auxiliary features from laser-Doppler vibrometer sensor}, booktitle = {10th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2016, Tianjin, China, October 17-20, 2016}, pages = {1--5}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ISCSLP.2016.7918400}, doi = {10.1109/ISCSLP.2016.7918400}, timestamp = {Mon, 20 Dec 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iscslp/XieDMXMW16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/XuHWJP16, author = {Yong Xu and Qiang Huang and Wenwu Wang and Philip J. B. Jackson and Mark D. Plumbley}, title = {Fully DNN-based Multi-label regression for audio tagging}, journal = {CoRR}, volume = {abs/1606.07695}, year = {2016}, url = {http://arxiv.org/abs/1606.07695}, eprinttype = {arXiv}, eprint = {1606.07695}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/XuHWJP16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/XuHWFSJP16, author = {Yong Xu and Qiang Huang and Wenwu Wang and Peter Foster and Siddharth Sigtia and Philip J. B. Jackson and Mark D. Plumbley}, title = {Fully Deep Neural Networks Incorporating Unsupervised Feature Learning for Audio Tagging}, journal = {CoRR}, volume = {abs/1607.03681}, year = {2016}, url = {http://arxiv.org/abs/1607.03681}, eprinttype = {arXiv}, eprint = {1607.03681}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/XuHWFSJP16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/XuHWP16, author = {Yong Xu and Qiang Huang and Wenwu Wang and Mark D. Plumbley}, title = {Hierachical learning for DNN-based acoustic scene classification}, journal = {CoRR}, volume = {abs/1607.03682}, year = {2016}, url = {http://arxiv.org/abs/1607.03682}, eprinttype = {arXiv}, eprint = {1607.03682}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/XuHWP16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/KongXWP16, author = {Qiuqiang Kong and Yong Xu and Wenwu Wang and Mark D. Plumbley}, title = {A Joint Detection-Classification Model for Audio Tagging of Weakly Labelled Data}, journal = {CoRR}, volume = {abs/1610.01797}, year = {2016}, url = {http://arxiv.org/abs/1610.01797}, eprinttype = {arXiv}, eprint = {1610.01797}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/KongXWP16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/XuDDL15, author = {Yong Xu and Jun Du and Li{-}Rong Dai and Chin{-}Hui Lee}, title = {A Regression Approach to Speech Enhancement Based on Deep Neural Networks}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {23}, number = {1}, pages = {7--19}, year = {2015}, url = {https://doi.org/10.1109/TASLP.2014.2364452}, doi = {10.1109/TASLP.2014.2364452}, timestamp = {Thu, 14 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/XuDDL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ica/GaoDXLDL15, author = {Tian Gao and Jun Du and Yong Xu and Cong Liu and Li{-}Rong Dai and Chin{-}Hui Lee}, editor = {Emmanuel Vincent and Arie Yeredor and Zbynek Koldovsk{\'{y}} and Petr Tichavsk{\'{y}}}, title = {Improving Deep Neural Network Based Speech Enhancement in Low {SNR} Environments}, booktitle = {Latent Variable Analysis and Signal Separation - 12th International Conference, {LVA/ICA} 2015, Liberec, Czech Republic, August 25-28, 2015, Proceedings}, series = {Lecture Notes in Computer Science}, volume = {9237}, pages = {75--82}, publisher = {Springer}, year = {2015}, url = {https://doi.org/10.1007/978-3-319-22482-4\_9}, doi = {10.1007/978-3-319-22482-4\_9}, timestamp = {Thu, 14 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ica/GaoDXLDL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XuDHDL15, author = {Yong Xu and Jun Du and Zhen Huang and Li{-}Rong Dai and Chin{-}Hui Lee}, title = {Multi-objective learning and mask-based post-processing for deep neural network based speech enhancement}, booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015}, pages = {1508--1512}, publisher = {{ISCA}}, year = {2015}, url = {https://doi.org/10.21437/Interspeech.2015-358}, doi = {10.21437/INTERSPEECH.2015-358}, timestamp = {Thu, 14 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XuDHDL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiHXL15, author = {Kehuang Li and Zhen Huang and Yong Xu and Chin{-}Hui Lee}, title = {DNN-based speech bandwidth expansion and its application to adding high-frequency missing features for automatic speech recognition of narrowband speech}, booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015}, pages = {2578--2582}, publisher = {{ISCA}}, year = {2015}, url = {https://doi.org/10.21437/Interspeech.2015-555}, doi = {10.21437/INTERSPEECH.2015-555}, timestamp = {Fri, 15 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LiHXL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/spl/XuDDL14, author = {Yong Xu and Jun Du and Li{-}Rong Dai and Chin{-}Hui Lee}, title = {An Experimental Study on Speech Enhancement Based on Deep Neural Networks}, journal = {{IEEE} Signal Process. Lett.}, volume = {21}, number = {1}, pages = {65--68}, year = {2014}, url = {https://doi.org/10.1109/LSP.2013.2291240}, doi = {10.1109/LSP.2013.2291240}, timestamp = {Thu, 14 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/spl/XuDDL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/chinasip/XuDDL14, author = {Yong Xu and Jun Du and Li{-}Rong Dai and Chin{-}Hui Lee}, title = {Global variance equalization for improving deep neural network based speech enhancement}, booktitle = {{IEEE} China Summit {\&} International Conference on Signal and Information Processing, ChinaSIP 2014, Xi'an, China, July 9-13, 2014}, pages = {71--75}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ChinaSIP.2014.6889204}, doi = {10.1109/CHINASIP.2014.6889204}, timestamp = {Thu, 14 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/chinasip/XuDDL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/DuWGXDL14, author = {Jun Du and Qing Wang and Tian Gao and Yong Xu and Li{-}Rong Dai and Chin{-}Hui Lee}, editor = {Haizhou Li and Helen M. Meng and Bin Ma and Engsiong Chng and Lei Xie}, title = {Robust speech recognition with speech enhanced deep neural networks}, booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, September 14-18, 2014}, pages = {616--620}, publisher = {{ISCA}}, year = {2014}, url = {https://doi.org/10.21437/Interspeech.2014-148}, doi = {10.21437/INTERSPEECH.2014-148}, timestamp = {Thu, 14 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/DuWGXDL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XuDDL14, author = {Yong Xu and Jun Du and Li{-}Rong Dai and Chin{-}Hui Lee}, editor = {Haizhou Li and Helen M. Meng and Bin Ma and Engsiong Chng and Lei Xie}, title = {Dynamic noise aware training for speech enhancement based on deep neural networks}, booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, September 14-18, 2014}, pages = {2670--2674}, publisher = {{ISCA}}, year = {2014}, url = {https://doi.org/10.21437/Interspeech.2014-571}, doi = {10.21437/INTERSPEECH.2014-571}, timestamp = {Thu, 14 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XuDDL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/TuDXDL14, author = {Yanhui Tu and Jun Du and Yong Xu and Li{-}Rong Dai and Chin{-}Hui Lee}, editor = {Minghui Dong and Jianhua Tao and Haizhou Li and Thomas Fang Zheng and Yanfeng Lu}, title = {Speech separation based on improved deep neural networks with dual outputs of speech features for both target and interfering speakers}, booktitle = {The 9th International Symposium on Chinese Spoken Language Processing, Singapore, September 12-14, 2014}, pages = {250--254}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ISCSLP.2014.6936615}, doi = {10.1109/ISCSLP.2014.6936615}, timestamp = {Mon, 18 Mar 2024 17:29:23 +0100}, biburl = {https://dblp.org/rec/conf/iscslp/TuDXDL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/XuDDL14, author = {Yong Xu and Jun Du and Li{-}Rong Dai and Chin{-}Hui Lee}, editor = {Minghui Dong and Jianhua Tao and Haizhou Li and Thomas Fang Zheng and Yanfeng Lu}, title = {Cross-language transfer learning for deep neural network based speech enhancement}, booktitle = {The 9th International Symposium on Chinese Spoken Language Processing, Singapore, September 12-14, 2014}, pages = {336--340}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ISCSLP.2014.6936608}, doi = {10.1109/ISCSLP.2014.6936608}, timestamp = {Thu, 14 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iscslp/XuDDL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.