Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Rongzhi Gu
@inproceedings{DBLP:conf/aaai/XuCYHWZLLG24,
author = {Yaoxun Xu and
Hangting Chen and
Jianwei Yu and
Qiaochu Huang and
Zhiyong Wu and
Shi{-}Xiong Zhang and
Guangzhi Li and
Yi Luo and
Rongzhi Gu},
editor = {Michael J. Wooldridge and
Jennifer G. Dy and
Sriraam Natarajan},
title = {SECap: Speech Emotion Captioning with Large Language Model},
booktitle = {Thirty-Eighth {AAAI} Conference on Artificial Intelligence, {AAAI}
2024, Thirty-Sixth Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2024, Fourteenth Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2014, February 20-27, 2024, Vancouver,
Canada},
pages = {19323--19331},
publisher = {{AAAI} Press},
year = {2024},
url = {https://doi.org/10.1609/aaai.v38i17.29902},
doi = {10.1609/AAAI.V38I17.29902},
timestamp = {Tue, 02 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/XuCYHWZLLG24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/GuZZY23,
author = {Rongzhi Gu and
Shi{-}Xiong Zhang and
Yuexian Zou and
Dong Yu},
title = {Towards Unified All-Neural Beamforming for Time and Frequency Domain
Speech Separation},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {31},
pages = {849--862},
year = {2023},
url = {https://doi.org/10.1109/TASLP.2022.3229261},
doi = {10.1109/TASLP.2022.3229261},
timestamp = {Fri, 10 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/GuZZY23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PengSGPMBC23,
author = {Junyi Peng and
Themos Stafylakis and
Rongzhi Gu and
Oldrich Plchot and
Ladislav Mosner and
Luk{\'{a}}s Burget and
Jan Cernock{\'{y}}},
title = {Parameter-Efficient Transfer Learning of Pre-Trained Transformer Models
for Speaker Verification Using Adapters},
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/ICASSP49357.2023.10094795},
doi = {10.1109/ICASSP49357.2023.10094795},
timestamp = {Sun, 05 Nov 2023 16:51:21 +0100},
biburl = {https://dblp.org/rec/conf/icassp/PengSGPMBC23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/YuCLGLW23,
author = {Jianwei Yu and
Hangting Chen and
Yi Luo and
Rongzhi Gu and
Weihua Li and
Chao Weng},
title = {TSpeech-AI System Description to the 5th Deep Noise Suppression {(DNS)}
Challenge},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
{ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
pages = {1--2},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/ICASSP49357.2023.10097210},
doi = {10.1109/ICASSP49357.2023.10097210},
timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/YuCLGLW23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2302-13462,
author = {Rongzhi Gu and
Shi{-}Xiong Zhang and
Dong Yu},
title = {3D Neural Beamforming for Multi-channel Speech Separation Against
Location Uncertainty},
journal = {CoRR},
volume = {abs/2302.13462},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2302.13462},
doi = {10.48550/ARXIV.2302.13462},
eprinttype = {arXiv},
eprint = {2302.13462},
timestamp = {Tue, 28 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2302-13462.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2304-08052,
author = {Yi Luo and
Rongzhi Gu},
title = {Fast Random Approximation of Multi-channel Room Impulse Response},
journal = {CoRR},
volume = {abs/2304.08052},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2304.08052},
doi = {10.48550/ARXIV.2304.08052},
eprinttype = {arXiv},
eprint = {2304.08052},
timestamp = {Fri, 21 Apr 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2304-08052.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2308-06981,
author = {Stefan Uhlich and
Giorgio Fabbro and
Masato Hirano and
Shusuke Takahashi and
Gordon Wichern and
Jonathan Le Roux and
Dipam Chakraborty and
Sharada P. Mohanty and
Kai Li and
Yi Luo and
Jianwei Yu and
Rongzhi Gu and
Roman A. Solovyev and
Alexander L. Stempkovskiy and
Tatiana Habruseva and
Mikhail Sukhovei and
Yuki Mitsufuji},
title = {The Sound Demixing Challenge 2023 - Cinematic Demixing Track},
journal = {CoRR},
volume = {abs/2308.06981},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2308.06981},
doi = {10.48550/ARXIV.2308.06981},
eprinttype = {arXiv},
eprint = {2308.06981},
timestamp = {Thu, 24 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2308-06981.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2308-11053,
author = {Hangting Chen and
Jianwei Yu and
Yi Luo and
Rongzhi Gu and
Weihua Li and
Zhuocheng Lu and
Chao Weng},
title = {Ultra Dual-Path Compression For Joint Echo Cancellation And Noise
Suppression},
journal = {CoRR},
volume = {abs/2308.11053},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2308.11053},
doi = {10.48550/ARXIV.2308.11053},
eprinttype = {arXiv},
eprint = {2308.11053},
timestamp = {Fri, 25 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2308-11053.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2308-16892,
author = {Rongzhi Gu and
Yi Luo},
title = {ReZero: Region-customizable Sound Extraction},
journal = {CoRR},
volume = {abs/2308.16892},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2308.16892},
doi = {10.48550/ARXIV.2308.16892},
eprinttype = {arXiv},
eprint = {2308.16892},
timestamp = {Fri, 01 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2308-16892.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2312-10381,
author = {Yaoxun Xu and
Hangting Chen and
Jianwei Yu and
Qiaochu Huang and
Zhiyong Wu and
Shi{-}Xiong Zhang and
Guangzhi Li and
Yi Luo and
Rongzhi Gu},
title = {SECap: Speech Emotion Captioning with Large Language Model},
journal = {CoRR},
volume = {abs/2312.10381},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2312.10381},
doi = {10.48550/ARXIV.2312.10381},
eprinttype = {arXiv},
eprint = {2312.10381},
timestamp = {Tue, 16 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2312-10381.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/XuGZ22,
author = {Xinmeng Xu and
Rongzhi Gu and
Yuexian Zou},
title = {Improving Dual-Microphone Speech Enhancement by Learning Cross-Channel
Features with Multi-Head Attention},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
pages = {6492--6496},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/ICASSP43922.2022.9746359},
doi = {10.1109/ICASSP43922.2022.9746359},
timestamp = {Tue, 07 Jun 2022 17:34:47 +0200},
biburl = {https://dblp.org/rec/conf/icassp/XuGZ22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/WangGZGWZ22,
author = {Li Wang and
Rongzhi Gu and
Weiji Zhuang and
Peng Gao and
Yujun Wang and
Yuexian Zou},
title = {Learning Decoupling Features Through Orthogonality Regularization},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
pages = {7562--7566},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/ICASSP43922.2022.9747878},
doi = {10.1109/ICASSP43922.2022.9747878},
timestamp = {Tue, 07 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/WangGZGWZ22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PengGMPBC22,
author = {Junyi Peng and
Rongzhi Gu and
Ladislav Mosner and
Oldrich Plchot and
Luk{\'{a}}s Burget and
Jan Cernock{\'{y}}},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Learnable Sparse Filterbank for Speaker Verification},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {5110--5114},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-11309},
doi = {10.21437/INTERSPEECH.2022-11309},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/PengGMPBC22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ZhaoGYTZ22,
author = {Zifeng Zhao and
Rongzhi Gu and
Dongchao Yang and
Jinchuan Tian and
Yuexian Zou},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Speaker-Aware Mixture of Mixtures Training for Weakly Supervised Speaker
Extraction},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {5318--5322},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-96},
doi = {10.21437/INTERSPEECH.2022-96},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ZhaoGYTZ22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ZhaoYGZZ22,
author = {Zifeng Zhao and
Dongchao Yang and
Rongzhi Gu and
Haoran Zhang and
Yuexian Zou},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Target Confusion in End-to-end Speaker Extraction: Analysis and Approaches},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {5333--5337},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-176},
doi = {10.21437/INTERSPEECH.2022-176},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ZhaoYGZZ22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-16772,
author = {Li Wang and
Rongzhi Gu and
Weiji Zhuang and
Peng Gao and
Yujun Wang and
Yuexian Zou},
title = {Learning Decoupling Features Through Orthogonality Regularization},
journal = {CoRR},
volume = {abs/2203.16772},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.16772},
doi = {10.48550/ARXIV.2203.16772},
eprinttype = {arXiv},
eprint = {2203.16772},
timestamp = {Mon, 04 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-16772.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-01355,
author = {Zifeng Zhao and
Dongchao Yang and
Rongzhi Gu and
Haoran Zhang and
Yuexian Zou},
title = {Target Confusion in End-to-end Speaker Extraction: Analysis and Approaches},
journal = {CoRR},
volume = {abs/2204.01355},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.01355},
doi = {10.48550/ARXIV.2204.01355},
eprinttype = {arXiv},
eprint = {2204.01355},
timestamp = {Wed, 06 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-01355.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-07375,
author = {Zifeng Zhao and
Rongzhi Gu and
Dongchao Yang and
Jinchuan Tian and
Yuexian Zou},
title = {Speaker-Aware Mixture of Mixtures Training for Weakly Supervised Speaker
Extraction},
journal = {CoRR},
volume = {abs/2204.07375},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.07375},
doi = {10.48550/ARXIV.2204.07375},
eprinttype = {arXiv},
eprint = {2204.07375},
timestamp = {Wed, 20 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-07375.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2205-01280,
author = {Xinmeng Xu and
Rongzhi Gu and
Yuexian Zou},
title = {Improving Dual-Microphone Speech Enhancement by Learning Cross-Channel
Features with Multi-Head Attention},
journal = {CoRR},
volume = {abs/2205.01280},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2205.01280},
doi = {10.48550/ARXIV.2205.01280},
eprinttype = {arXiv},
eprint = {2205.01280},
timestamp = {Thu, 05 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2205-01280.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-16032,
author = {Junyi Peng and
Themos Stafylakis and
Rongzhi Gu and
Oldrich Plchot and
Ladislav Mosner and
Luk{\'{a}}s Burget and
Jan Cernock{\'{y}}},
title = {Parameter-efficient transfer learning of pre-trained Transformer models
for speaker verification using adapters},
journal = {CoRR},
volume = {abs/2210.16032},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.16032},
doi = {10.48550/ARXIV.2210.16032},
eprinttype = {arXiv},
eprint = {2210.16032},
timestamp = {Thu, 03 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-16032.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-08348,
author = {Rongzhi Gu and
Shi{-}Xiong Zhang and
Yuexian Zou and
Dong Yu},
title = {Towards Unified All-Neural Beamforming for Time and Frequency Domain
Speech Separation},
journal = {CoRR},
volume = {abs/2212.08348},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2212.08348},
doi = {10.48550/ARXIV.2212.08348},
eprinttype = {arXiv},
eprint = {2212.08348},
timestamp = {Mon, 02 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2212-08348.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/spl/GuZZY21,
author = {Rongzhi Gu and
Shi{-}Xiong Zhang and
Yuexian Zou and
Dong Yu},
title = {Complex Neural Spatial Filter: Enhancing Multi-Channel Target Speech
Separation in Complex Domain},
journal = {{IEEE} Signal Process. Lett.},
volume = {28},
pages = {1370--1374},
year = {2021},
url = {https://doi.org/10.1109/LSP.2021.3076374},
doi = {10.1109/LSP.2021.3076374},
timestamp = {Thu, 16 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/spl/GuZZY21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/GuZYY21,
author = {Rongzhi Gu and
Shi{-}Xiong Zhang and
Meng Yu and
Dong Yu},
title = {3D Spatial Features for Multi-Channel Target Speech Separation},
booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU}
2021, Cartagena, Colombia, December 13-17, 2021},
pages = {996--1002},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ASRU51503.2021.9688198},
doi = {10.1109/ASRU51503.2021.9688198},
timestamp = {Wed, 09 Feb 2022 09:03:03 +0100},
biburl = {https://dblp.org/rec/conf/asru/GuZYY21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PengQWG0BC21,
author = {Junyi Peng and
Xiaoyang Qu and
Jianzong Wang and
Rongzhi Gu and
Jing Xiao and
Luk{\'{a}}s Burget and
Jan Cernock{\'{y}}},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {ICSpk: Interpretable Complex Speaker Embedding Extractor from Raw
Waveform},
booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech
Communication Association, Brno, Czechia, 30 August - 3 September
2021},
pages = {511--515},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-2016},
doi = {10.21437/INTERSPEECH.2021-2016},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/PengQWG0BC21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/PengQGWXBC21,
author = {Junyi Peng and
Xiaoyang Qu and
Rongzhi Gu and
Jianzong Wang and
Jing Xiao and
Luk{\'{a}}s Burget and
Jan Cernock{\'{y}}},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {Effective Phase Encoding for End-To-End Speaker Verification},
booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech
Communication Association, Brno, Czechia, 30 August - 3 September
2021},
pages = {2366--2370},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-2025},
doi = {10.21437/INTERSPEECH.2021-2025},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/PengQGWXBC21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/WangGCZ21,
author = {Li Wang and
Rongzhi Gu and
Nuo Chen and
Yuexian Zou},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {Text Anchor Based Metric Learning for Small-Footprint Keyword Spotting},
booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech
Communication Association, Brno, Czechia, 30 August - 3 September
2021},
pages = {4219--4223},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-136},
doi = {10.21437/INTERSPEECH.2021-136},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/WangGCZ21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-12359,
author = {Rongzhi Gu and
Shi{-}Xiong Zhang and
Yuexian Zou and
Dong Yu},
title = {Complex Neural Spatial Filter: Enhancing Multi-channel Target Speech
Separation in Complex Domain},
journal = {CoRR},
volume = {abs/2104.12359},
year = {2021},
url = {https://arxiv.org/abs/2104.12359},
eprinttype = {arXiv},
eprint = {2104.12359},
timestamp = {Mon, 03 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2104-12359.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2105-00812,
author = {Jinchuan Tian and
Rongzhi Gu and
Helin Wang and
Yuexian Zou},
title = {Layer Reduction: Accelerating Conformer-Based Self-Supervised Model
via Layer Consistency},
journal = {CoRR},
volume = {abs/2105.00812},
year = {2021},
url = {https://arxiv.org/abs/2105.00812},
eprinttype = {arXiv},
eprint = {2105.00812},
timestamp = {Wed, 12 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2105-00812.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2108-05516,
author = {Li Wang and
Rongzhi Gu and
Nuo Chen and
Yuexian Zou},
title = {Text Anchor Based Metric Learning for Small-footprint Keyword Spotting},
journal = {CoRR},
volume = {abs/2108.05516},
year = {2021},
url = {https://arxiv.org/abs/2108.05516},
eprinttype = {arXiv},
eprint = {2108.05516},
timestamp = {Wed, 18 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2108-05516.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}
}
@inproceedings{DBLP:conf/apsipa/PengGZZ20,
author = {Junyi Peng and
Rongzhi Gu and
Haoran Zhang and
Yuexian Zou},
title = {Context-adaptive Gaussian Attention for Text-independent Speaker Verification},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2020, Auckland, New Zealand, December
7-10, 2020},
pages = {595--599},
publisher = {{IEEE}},
year = {2020},
url = {https://ieeexplore.ieee.org/document/9306469},
timestamp = {Thu, 11 Feb 2021 11:44:30 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/PengGZZ20.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/PengGZ20,
author = {Junyi Peng and
Rongzhi Gu and
Yuexian Zou},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {Deep Speaker Embedding with Long Short Term Centroid Learning for
Text-Independent Speaker Verification},
booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech
Communication Association, Virtual Event, Shanghai, China, 25-29 October
2020},
pages = {3246--3250},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-2470},
doi = {10.21437/INTERSPEECH.2020-2470},
timestamp = {Fri, 29 Jan 2021 17:40:16 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/PengGZ20.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-2001-00391,
author = {Rongzhi Gu and
Yuexian Zou},
title = {Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel
Target Speech Separation},
journal = {CoRR},
volume = {abs/2001.00391},
year = {2020},
url = {http://arxiv.org/abs/2001.00391},
eprinttype = {arXiv},
eprint = {2001.00391},
timestamp = {Fri, 10 Jan 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2001-00391.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-2005-08571,
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}
}
@inproceedings{DBLP:conf/apsipa/PengGZW19,
author = {Junyi Peng and
Rongzhi Gu and
Yuexian Zou and
Wenwu Wang},
title = {Speaker-discriminative Embedding Learning via Affinity Matrix for
Short Utterance Speaker Verification},
booktitle = {2019 Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2019, Lanzhou, China, November
18-21, 2019},
pages = {314--319},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/APSIPAASC47483.2019.9023024},
doi = {10.1109/APSIPAASC47483.2019.9023024},
timestamp = {Thu, 05 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/PengGZW19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/GuPZ019,
author = {Rongzhi Gu and
Junyi Peng and
Yuexian Zou and
Dong Yu},
title = {Alleviate Cross-chunk Permutation through Chunk-level Speaker Embedding
for Blind Speech Separation},
booktitle = {2019 Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2019, Lanzhou, China, November
18-21, 2019},
pages = {325--331},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/APSIPAASC47483.2019.9023256},
doi = {10.1109/APSIPAASC47483.2019.9023256},
timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/GuPZ019.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/PengGZ19,
author = {Junyi Peng and
Rongzhi Gu and
Yuexian Zou},
title = {Logistic Similarity Metric Learning via Affinity Matrix for Text-Independent
Speaker Verification},
booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU}
2019, Singapore, December 14-18, 2019},
pages = {704--709},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ASRU46091.2019.9003995},
doi = {10.1109/ASRU46091.2019.9003995},
timestamp = {Mon, 24 Feb 2020 17:51:31 +0100},
biburl = {https://dblp.org/rec/conf/asru/PengGZ19.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 17:41:10 +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-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/cem/SuGHC17,
author = {Xin Su and
Rongzhi Gu and
Guangjie Han and
Dongmin Choi},
title = {Interaction Data Detection System to Upgrade Brick and Mortar Shops:
Metrics Allow Offline Shops to Compete with Online Retailers},
journal = {{IEEE} Consumer Electron. Mag.},
volume = {6},
number = {4},
pages = {57--63},
year = {2017},
url = {https://doi.org/10.1109/MCE.2017.2714422},
doi = {10.1109/MCE.2017.2714422},
timestamp = {Thu, 18 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/cem/SuGHC17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/ZouGWJR17,
author = {Yuexian Zou and
Rongzhi Gu and
Disong Wang and
Aimin Jiang and
Christian H. Ritz},
title = {Learning a robust {DOA} estimation model with acoustic vector sensor
cues},
booktitle = {2017 Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2017, Kuala Lumpur, Malaysia,
December 12-15, 2017},
pages = {1688--1691},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/APSIPA.2017.8282304},
doi = {10.1109/APSIPA.2017.8282304},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/ZouGWJR17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
a service of 
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.
last updated on 2024-04-25 01:46 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
