Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Dong Wang 0013
@article{DBLP:journals/apin/LiWAW24,
author = {Lantian Li and
Di Wang and
Andrew Abel and
Dong Wang},
title = {On evaluation trials in speaker verification},
journal = {Appl. Intell.},
volume = {54},
number = {1},
pages = {113--130},
year = {2024},
url = {https://doi.org/10.1007/s10489-023-05071-9},
doi = {10.1007/S10489-023-05071-9},
timestamp = {Sat, 10 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/apin/LiWAW24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pr/CaiLAZW24,
author = {Yunqi Cai and
Lantian Li and
Andrew Abel and
Xiaoyan Zhu and
Dong Wang},
title = {Maximum Gaussianality training for deep speaker vector normalization},
journal = {Pattern Recognit.},
volume = {145},
pages = {109977},
year = {2024},
url = {https://doi.org/10.1016/j.patcog.2023.109977},
doi = {10.1016/J.PATCOG.2023.109977},
timestamp = {Tue, 24 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/pr/CaiLAZW24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-02730,
author = {Pengqi Li and
Tianhao Wang and
Lantian Li and
Askar Hamdulla and
Dong Wang},
title = {How phonemes contribute to deep speaker models?},
journal = {CoRR},
volume = {abs/2402.02730},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.02730},
doi = {10.48550/ARXIV.2402.02730},
eprinttype = {arXiv},
eprint = {2402.02730},
timestamp = {Wed, 10 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-02730.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pami/SunWLCZ23,
author = {Haoran Sun and
Dong Wang and
Lantian Li and
Chen Chen and
Thomas Fang Zheng},
title = {Random Cycle Loss and Its Application to Voice Conversion},
journal = {{IEEE} Trans. Pattern Anal. Mach. Intell.},
volume = {45},
number = {8},
pages = {10331--10345},
year = {2023},
url = {https://doi.org/10.1109/TPAMI.2023.3257839},
doi = {10.1109/TPAMI.2023.3257839},
timestamp = {Fri, 21 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/pami/SunWLCZ23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ChenWZ23,
author = {Chen Chen and
Dong Wang and
Thomas Fang Zheng},
title = {{CN-CVS:} {A} Mandarin Audio-Visual Dataset for Large Vocabulary Continuous
Visual to Speech Synthesis},
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/ICASSP49357.2023.10095796},
doi = {10.1109/ICASSP49357.2023.10095796},
timestamp = {Sun, 05 Nov 2023 16:51:21 +0100},
biburl = {https://dblp.org/rec/conf/icassp/ChenWZ23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ococosda/YouN0CDH023,
author = {Zhenghai You and
Mewlude Nijat and
Ying Shi and
Chen Chen and
Wenqiang Du and
Askar Hamdulla and
Dong Wang},
title = {Zero-shot Mispronunciation Detection by Knowledge-based Data Augmentation},
booktitle = {26th Conference of the Oriental {COCOSDA} International Committee
for the Co-ordination and Standardisation of Speech Databases and
Assessment Techniques, {O-COCOSDA} 2023, Delhi, India, December 4-6,
2023},
pages = {1--6},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/O-COCOSDA60357.2023.10482946},
doi = {10.1109/O-COCOSDA60357.2023.10482946},
timestamp = {Wed, 10 Apr 2024 17:21:48 +0200},
biburl = {https://dblp.org/rec/conf/ococosda/YouN0CDH023.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-16049,
author = {Lantian Li and
Xiaolou Li and
Haoyu Jiang and
Chen Chen and
Ruihai Hou and
Dong Wang},
title = {CN-Celeb-AV: {A} Multi-Genre Audio-Visual Dataset for Person Recognition},
journal = {CoRR},
volume = {abs/2305.16049},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.16049},
doi = {10.48550/ARXIV.2305.16049},
eprinttype = {arXiv},
eprint = {2305.16049},
timestamp = {Wed, 10 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-16049.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-16070,
author = {Pengqi Li and
Lantian Li and
Askar Hamdulla and
Dong Wang},
title = {Visualizing data augmentation in deep speaker recognition},
journal = {CoRR},
volume = {abs/2305.16070},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.16070},
doi = {10.48550/ARXIV.2305.16070},
eprinttype = {arXiv},
eprint = {2305.16070},
timestamp = {Wed, 10 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-16070.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-17706,
author = {Ying Shi and
Dong Wang and
Lantian Li and
Jiqing Han and
Shi Yin},
title = {Spot keywords from very noisy and mixed speech},
journal = {CoRR},
volume = {abs/2305.17706},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.17706},
doi = {10.48550/ARXIV.2305.17706},
eprinttype = {arXiv},
eprint = {2305.17706},
timestamp = {Thu, 26 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-17706.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-05352,
author = {Ying Shi and
Dong Wang and
Lantian Li and
Jiqing Han},
title = {A Glance is Enough: Extract Target Sentence By Looking at {A} keyword},
journal = {CoRR},
volume = {abs/2310.05352},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.05352},
doi = {10.48550/ARXIV.2310.05352},
eprinttype = {arXiv},
eprint = {2310.05352},
timestamp = {Thu, 26 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-05352.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/LiLKFCCVZW22,
author = {Lantian Li and
Ruiqi Liu and
Jiawen Kang and
Yue Fan and
Hao Cui and
Yunqi Cai and
Ravichander Vipperla and
Thomas Fang Zheng and
Dong Wang},
title = {CN-Celeb: Multi-genre speaker recognition},
journal = {Speech Commun.},
volume = {137},
pages = {77--91},
year = {2022},
url = {https://doi.org/10.1016/j.specom.2022.01.002},
doi = {10.1016/J.SPECOM.2022.01.002},
timestamp = {Fri, 01 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/speech/LiLKFCCVZW22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/LiWKWWGC22,
author = {Lantian Li and
Dong Wang and
Jiawen Kang and
Renyu Wang and
Jing Wu and
Zhendong Gao and
Xiao Chen},
title = {A Principle Solution for Enroll-Test Mismatch in Speaker Recognition},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {30},
pages = {443--455},
year = {2022},
url = {https://doi.org/10.1109/TASLP.2022.3140558},
doi = {10.1109/TASLP.2022.3140558},
timestamp = {Wed, 03 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/LiWKWWGC22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LiNW22,
author = {Lantian Li and
Ruiqian Nai and
Dong Wang},
title = {Real Additive Margin Softmax for Speaker Verification},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
pages = {7527--7531},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/ICASSP43922.2022.9747166},
doi = {10.1109/ICASSP43922.2022.9747166},
timestamp = {Tue, 07 Jun 2022 17:34:47 +0200},
biburl = {https://dblp.org/rec/conf/icassp/LiNW22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiLHW22,
author = {Pengqi Li and
Lantian Li and
Askar Hamdulla and
Dong Wang},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Reliable Visualization for Deep Speaker Recognition},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {331--335},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-926},
doi = {10.21437/INTERSPEECH.2022-926},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiLHW22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/odyssey/SunCLW22,
author = {Haoran Sun and
Chen Chen and
Lantian Li and
Dong Wang},
editor = {Thomas Fang Zheng},
title = {Cycleflow: Purify Information Factors by Cycle Loss},
booktitle = {Odyssey 2022: The Speaker and Language Recognition Workshop, 28 June
- 1 July 2022, Beijing, China},
pages = {271--278},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Odyssey.2022-38},
doi = {10.21437/ODYSSEY.2022-38},
timestamp = {Tue, 27 Sep 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/odyssey/SunCLW22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/odyssey/LiWDW22,
author = {Lantian Li and
Di Wang and
Wenqiang Du and
Dong Wang},
editor = {Thomas Fang Zheng},
title = {{C-P} Map: {A} Novel Evaluation Toolkit for Speaker Verification},
booktitle = {Odyssey 2022: The Speaker and Language Recognition Workshop, 28 June
- 1 July 2022, Beijing, China},
pages = {306--313},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Odyssey.2022-43},
doi = {10.21437/ODYSSEY.2022-43},
timestamp = {Tue, 27 Sep 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/odyssey/LiWDW22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-02942,
author = {Lantian Li and
Di Wang and
Wenqiang Du and
Dong Wang},
title = {{C-P} Map: {A} Novel Evaluation Toolkit for Speaker Verification},
journal = {CoRR},
volume = {abs/2203.02942},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.02942},
doi = {10.48550/ARXIV.2203.02942},
eprinttype = {arXiv},
eprint = {2203.02942},
timestamp = {Wed, 16 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-02942.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-03847,
author = {Weida Liang and
Lantian Li and
Wenqiang Du and
Dong Wang},
title = {Enhanced exemplar autoencoder with cycle consistency loss in any-to-one
voice conversion},
journal = {CoRR},
volume = {abs/2204.03847},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.03847},
doi = {10.48550/ARXIV.2204.03847},
eprinttype = {arXiv},
eprint = {2204.03847},
timestamp = {Tue, 27 Sep 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-03847.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-03852,
author = {Pengqi Li and
Lantian Li and
Askar Hamdulla and
Dong Wang},
title = {Reliable Visualization for Deep Speaker Recognition},
journal = {CoRR},
volume = {abs/2204.03852},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.03852},
doi = {10.48550/ARXIV.2204.03852},
eprinttype = {arXiv},
eprint = {2204.03852},
timestamp = {Tue, 27 Sep 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-03852.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2209-04687,
author = {Lantian Li and
Di Wang and
Dong Wang},
title = {Pay Attention to Hard Trials},
journal = {CoRR},
volume = {abs/2209.04687},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2209.04687},
doi = {10.48550/ARXIV.2209.04687},
eprinttype = {arXiv},
eprint = {2209.04687},
timestamp = {Tue, 27 Sep 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2209-04687.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/CaiLAZ021,
author = {Yunqi Cai and
Lantian Li and
Andrew Abel and
Xiaoyan Zhu and
Dong Wang},
title = {Deep Normalization for Speaker Vectors},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {29},
pages = {733--744},
year = {2021},
url = {https://doi.org/10.1109/TASLP.2020.3039573},
doi = {10.1109/TASLP.2020.3039573},
timestamp = {Sat, 28 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/CaiLAZ021.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/WangLYW21,
author = {Di Wang and
Lantian Li and
Hongzhi Yu and
Dong Wang},
title = {A Study on Decoupled Probabilistic Linear Discriminant Analysis},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2021, Tokyo, Japan, December
14-17, 2021},
pages = {713--718},
publisher = {{IEEE}},
year = {2021},
url = {https://ieeexplore.ieee.org/document/9689621},
timestamp = {Mon, 14 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/WangLYW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/SunLZW21,
author = {Haoran Sun and
Lantian Li and
Thomas Fang Zheng and
Dong Wang},
title = {How Speech is Recognized to Be Emotional - {A} Study Based on Information
Decomposition},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2021, Tokyo, Japan, December
14-17, 2021},
pages = {780--785},
publisher = {{IEEE}},
year = {2021},
url = {https://ieeexplore.ieee.org/document/9689548},
timestamp = {Wed, 09 Feb 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/SunLZW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/WangHLZLHLWSY21,
author = {Binling Wang and
Wenxuan Hu and
Jing Li and
Yiming Zhi and
Zheng Li and
Qingyang Hong and
Lin Li and
Dong Wang and
Liming Song and
Cheng Yang},
title = {{OLR} 2021 Challenge: Datasets, Rules and Baselines},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2021, Tokyo, Japan, December
14-17, 2021},
pages = {1097--1103},
publisher = {{IEEE}},
year = {2021},
url = {https://ieeexplore.ieee.org/document/9689463},
timestamp = {Thu, 05 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/WangHLZLHLWSY21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/HanCLLW21,
author = {Jiao Han and
Yunqi Cai and
Lantian Li and
Guanyu Li and
Dong Wang},
title = {An {MAP} Estimation for Between-Class Variance},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2021, Tokyo, Japan, December
14-17, 2021},
pages = {1121--1126},
publisher = {{IEEE}},
year = {2021},
url = {https://ieeexplore.ieee.org/document/9689627},
timestamp = {Wed, 09 Feb 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/HanCLLW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LiZKZ021,
author = {Lantian Li and
Yang Zhang and
Jiawen Kang and
Thomas Fang Zheng and
Dong Wang},
title = {Squeezing Value of Cross-Domain Labels: {A} Decoupled Scoring Approach
for Speaker Verification},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
pages = {5829--5833},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ICASSP39728.2021.9414794},
doi = {10.1109/ICASSP39728.2021.9414794},
timestamp = {Mon, 12 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/LiZKZ021.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiWZLLHW21,
author = {Jing Li and
Binling Wang and
Yiming Zhi and
Zheng Li and
Lin Li and
Qingyang Hong and
Dong Wang},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {Oriental Language Recognition {(OLR)} 2020: Summary and Analysis},
booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech
Communication Association, Brno, Czechia, 30 August - 3 September
2021},
pages = {3251--3255},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-2171},
doi = {10.21437/INTERSPEECH.2021-2171},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiWZLLHW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/Tang0XSLZWTXZYL21,
author = {Zhiyuan Tang and
Dong Wang and
Yanguang Xu and
Jianwei Sun and
Xiaoning Lei and
Shuaijiang Zhao and
Cheng Wen and
Xingjun Tan and
Chuandong Xie and
Shuran Zhou and
Rui Yan and
Chenjia Lv and
Yang Han and
Wei Zou and
Xiangang Li},
editor = {Joaquin Vanschoren and
Sai{-}Kit Yeung},
title = {KeSpeech: An Open Source Speech Dataset of Mandarin and Its Eight
Subdialects},
booktitle = {Proceedings of the Neural Information Processing Systems Track on
Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021, December
2021, virtual},
year = {2021},
url = {https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/0336dcbab05b9d5ad24f4333c7658a0e-Abstract-round2.html},
timestamp = {Thu, 05 May 2022 16:30:03 +0200},
biburl = {https://dblp.org/rec/conf/nips/Tang0XSLZWTXZYL21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ococosda/ZhiSDLW21,
author = {Tiankai Zhi and
Ying Shi and
Wenqiang Du and
Guanyu Li and
Dong Wang},
title = {{M2ASR-MONGO:} {A} Free Mongolian Speech Database and Accompanied
Baselines},
booktitle = {24th Conference of the Oriental {COCOSDA} International Committee
for the Co-ordination and Standardisation of Speech Databases and
Assessment Techniques, {O-COCOSDA} 2021, Singapore, November 18-20,
2021},
pages = {140--145},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/O-COCOSDA202152914.2021.9660401},
doi = {10.1109/O-COCOSDA202152914.2021.9660401},
timestamp = {Wed, 10 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ococosda/ZhiSDLW21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/ShiCTL0H21,
author = {Ying Shi and
Haolin Chen and
Zhiyuan Tang and
Lantian Li and
Dong Wang and
Jiqing Han},
title = {Can We Trust Deep Speech Prior?},
booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen,
China, January 19-22, 2021},
pages = {742--749},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/SLT48900.2021.9383499},
doi = {10.1109/SLT48900.2021.9383499},
timestamp = {Thu, 26 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/slt/ShiCTL0H21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2107-05365,
author = {Jing Li and
Binling Wang and
Yiming Zhi and
Zheng Li and
Lin Li and
Qingyang Hong and
Dong Wang},
title = {Oriental Language Recognition {(OLR)} 2020: Summary and Analysis},
journal = {CoRR},
volume = {abs/2107.05365},
year = {2021},
url = {https://arxiv.org/abs/2107.05365},
eprinttype = {arXiv},
eprint = {2107.05365},
timestamp = {Thu, 05 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2107-05365.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2107-11113,
author = {Binling Wang and
Wenxuan Hu and
Jing Li and
Yiming Zhi and
Zheng Li and
Qingyang Hong and
Lin Li and
Dong Wang and
Liming Song and
Cheng Yang},
title = {{OLR} 2021 Challenge: Datasets, Rules and Baselines},
journal = {CoRR},
volume = {abs/2107.11113},
year = {2021},
url = {https://arxiv.org/abs/2107.11113},
eprinttype = {arXiv},
eprint = {2107.11113},
timestamp = {Thu, 05 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2107-11113.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-09116,
author = {Lantian Li and
Ruiqian Nai and
Dong Wang},
title = {Real Additive Margin Softmax for Speaker Verification},
journal = {CoRR},
volume = {abs/2110.09116},
year = {2021},
url = {https://arxiv.org/abs/2110.09116},
eprinttype = {arXiv},
eprint = {2110.09116},
timestamp = {Mon, 14 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-09116.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-09928,
author = {Haoran Sun and
Chen Chen and
Lantian Li and
Dong Wang},
title = {CycleFlow: Purify Information Factors by Cycle Loss},
journal = {CoRR},
volume = {abs/2110.09928},
year = {2021},
url = {https://arxiv.org/abs/2110.09928},
eprinttype = {arXiv},
eprint = {2110.09928},
timestamp = {Mon, 14 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-09928.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2111-12324,
author = {Haoran Sun and
Lantian Li and
Thomas Fang Zheng and
Dong Wang},
title = {How Speech is Recognized to Be Emotional - {A} Study Based on Information
Decomposition},
journal = {CoRR},
volume = {abs/2111.12324},
year = {2021},
url = {https://arxiv.org/abs/2111.12324},
eprinttype = {arXiv},
eprint = {2111.12324},
timestamp = {Mon, 14 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2111-12324.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2111-12326,
author = {Di Wang and
Lantian Li and
Hongzhi Yu and
Dong Wang},
title = {A Study on Decoupled Probabilistic Linear Discriminant Analysis},
journal = {CoRR},
volume = {abs/2111.12326},
year = {2021},
url = {https://arxiv.org/abs/2111.12326},
eprinttype = {arXiv},
eprint = {2111.12326},
timestamp = {Mon, 14 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2111-12326.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2111-12331,
author = {Jiao Han and
Yunqi Cai and
Lantian Li and
Guanyu Li and
Dong Wang},
title = {An {MAP} Estimation for Between-Class Variance},
journal = {CoRR},
volume = {abs/2111.12331},
year = {2021},
url = {https://arxiv.org/abs/2111.12331},
eprinttype = {arXiv},
eprint = {2111.12331},
timestamp = {Mon, 14 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2111-12331.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/LiZHLTWSY20,
author = {Zheng Li and
Miao Zhao and
Qingyang Hong and
Lin Li and
Zhiyuan Tang and
Dong Wang and
Liming Song and
Cheng Yang},
title = {{AP20-OLR} Challenge: Three Tasks and Their Baselines},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2020, Auckland, New Zealand, December
7-10, 2020},
pages = {550--555},
publisher = {{IEEE}},
year = {2020},
url = {https://ieeexplore.ieee.org/document/9306442},
timestamp = {Thu, 05 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/LiZHLTWSY20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/WangX0CS20,
author = {Wupeng Wang and
Chao Xing and
Dong Wang and
Xiao Chen and
Fengyu Sun},
title = {A Robust Audio-Visual Speech Enhancement Model},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {7529--7533},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9053033},
doi = {10.1109/ICASSP40776.2020.9053033},
timestamp = {Wed, 03 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/WangX0CS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ChengLLTWZ20,
author = {Sitong Cheng and
Zhixin Liu and
Lantian Li and
Zhiyuan Tang and
Dong Wang and
Thomas Fang Zheng},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {ASR-Free Pronunciation Assessment},
booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech
Communication Association, Virtual Event, Shanghai, China, 25-29 October
2020},
pages = {3047--3051},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-2623},
doi = {10.21437/INTERSPEECH.2020-2623},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ChengLLTWZ20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiWZ20,
author = {Lantian Li and
Dong Wang and
Thomas Fang Zheng},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {Neural Discriminant Analysis for Deep Speaker Embedding},
booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech
Communication Association, Virtual Event, Shanghai, China, 25-29 October
2020},
pages = {3251--3255},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-2542},
doi = {10.21437/INTERSPEECH.2020-2542},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiWZ20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KangLLCWZ20,
author = {Jiawen Kang and
Ruiqi Liu and
Lantian Li and
Yunqi Cai and
Dong Wang and
Thomas Fang Zheng},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {Domain-Invariant Speaker Vector Projection by Model-Agnostic Meta-Learning},
booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech
Communication Association, Virtual Event, Shanghai, China, 25-29 October
2020},
pages = {3825--3829},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-2562},
doi = {10.21437/INTERSPEECH.2020-2562},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KangLLCWZ20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2004-04095,
author = {Yunqi Cai and
Lantian Li and
Dong Wang and
Andrew Abel},
title = {Deep Normalization for Speaker Vectors},
journal = {CoRR},
volume = {abs/2004.04095},
year = {2020},
url = {https://arxiv.org/abs/2004.04095},
eprinttype = {arXiv},
eprint = {2004.04095},
timestamp = {Fri, 24 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2004-04095.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-03473,
author = {Zheng Li and
Miao Zhao and
Qingyang Hong and
Lin Li and
Zhiyuan Tang and
Dong Wang and
Liming Song and
Cheng Yang},
title = {{AP20-OLR} Challenge: Three Tasks and Their Baselines},
journal = {CoRR},
volume = {abs/2006.03473},
year = {2020},
url = {https://arxiv.org/abs/2006.03473},
eprinttype = {arXiv},
eprint = {2006.03473},
timestamp = {Thu, 05 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2006-03473.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-14242,
author = {Haoran Sun and
Lantian Li and
Yunqi Cai and
Yang Zhang and
Thomas Fang Zheng and
Dong Wang},
title = {Deep generative factorization for speech signal},
journal = {CoRR},
volume = {abs/2010.14242},
year = {2020},
url = {https://arxiv.org/abs/2010.14242},
eprinttype = {arXiv},
eprint = {2010.14242},
timestamp = {Wed, 17 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-14242.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-14243,
author = {Lantian Li and
Yang Zhang and
Jiawen Kang and
Thomas Fang Zheng and
Dong Wang},
title = {Squeezing value of cross-domain labels: a decoupled scoring approach
for speaker verification},
journal = {CoRR},
volume = {abs/2010.14243},
year = {2020},
url = {https://arxiv.org/abs/2010.14243},
eprinttype = {arXiv},
eprint = {2010.14243},
timestamp = {Thu, 08 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-14243.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-16138,
author = {Yunqi Cai and
Dong Wang},
title = {Deep generative {LDA}},
journal = {CoRR},
volume = {abs/2010.16138},
year = {2020},
url = {https://arxiv.org/abs/2010.16138},
eprinttype = {arXiv},
eprint = {2010.16138},
timestamp = {Wed, 17 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-16138.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-16148,
author = {Yunqi Cai and
Lantian Li and
Dong Wang and
Andrew Abel},
title = {Deep Speaker Vector Normalization with Maximum Gaussianality Training},
journal = {CoRR},
volume = {abs/2010.16148},
year = {2020},
url = {https://arxiv.org/abs/2010.16148},
eprinttype = {arXiv},
eprint = {2010.16148},
timestamp = {Wed, 17 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-16148.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-02110,
author = {Ying Shi and
Haolin Chen and
Zhiyuan Tang and
Lantian Li and
Dong Wang and
Jiqing Han},
title = {Can We Trust Deep Speech Prior?},
journal = {CoRR},
volume = {abs/2011.02110},
year = {2020},
url = {https://arxiv.org/abs/2011.02110},
eprinttype = {arXiv},
eprint = {2011.02110},
timestamp = {Thu, 26 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2011-02110.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2012-12468,
author = {Lantian Li and
Ruiqi Liu and
Jiawen Kang and
Yue Fan and
Hao Cui and
Yunqi Cai and
Ravichander Vipperla and
Thomas Fang Zheng and
Dong Wang},
title = {CN-Celeb: multi-genre speaker recognition},
journal = {CoRR},
volume = {abs/2012.12468},
year = {2020},
url = {https://arxiv.org/abs/2012.12468},
eprinttype = {arXiv},
eprint = {2012.12468},
timestamp = {Wed, 17 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2012-12468.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2012-12471,
author = {Lantian Li and
Dong Wang and
Jiawen Kang and
Renyu Wang and
Jing Wu and
Zhendong Gao and
Xiao Chen},
title = {A Principle Solution for Enroll-Test Mismatch in Speaker Recognition},
journal = {CoRR},
volume = {abs/2012.12471},
year = {2020},
url = {https://arxiv.org/abs/2012.12471},
eprinttype = {arXiv},
eprint = {2012.12471},
timestamp = {Wed, 03 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2012-12471.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/LiTS019,
author = {Lantian Li and
Zhiyuan Tang and
Ying Shi and
Dong Wang},
title = {Phonetic-Attention Scoring for Deep Speaker Features in 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 = {284--288},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/APSIPAASC47483.2019.9023352},
doi = {10.1109/APSIPAASC47483.2019.9023352},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/LiTS019.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/CaiW19,
author = {Yunqi Cai and
Dong Wang},
title = {Question Mark Prediction By Bert},
booktitle = {2019 Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2019, Lanzhou, China, November
18-21, 2019},
pages = {363--367},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/APSIPAASC47483.2019.9023090},
doi = {10.1109/APSIPAASC47483.2019.9023090},
timestamp = {Wed, 17 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/CaiW19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/WuTW19,
author = {Jiayao Wu and
Zhiyuan Tang and
Dong Wang},
title = {Structure Growth for Small-Footprint Speech Recognition},
booktitle = {2019 Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2019, Lanzhou, China, November
18-21, 2019},
pages = {461--465},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/APSIPAASC47483.2019.9023275},
doi = {10.1109/APSIPAASC47483.2019.9023275},
timestamp = {Thu, 05 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/WuTW19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/WangLW19,
author = {Xueyi Wang and
Lantian Li and
Dong Wang},
title = {VAE-based Domain Adaptation for 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 = {535--539},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/APSIPAASC47483.2019.9023015},
doi = {10.1109/APSIPAASC47483.2019.9023015},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/WangLW19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/TangWS19,
author = {Zhiyuan Tang and
Dong Wang and
Liming Song},
title = {{AP19-OLR} Challenge: Three Tasks and Their Baselines},
booktitle = {2019 Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2019, Lanzhou, China, November
18-21, 2019},
pages = {1917--1921},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/APSIPAASC47483.2019.9023321},
doi = {10.1109/APSIPAASC47483.2019.9023321},
timestamp = {Mon, 16 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/TangWS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LiTSW19,
author = {Lantian Li and
Zhiyuan Tang and
Ying Shi and
Dong Wang},
title = {Gaussian-constrained Training for Speaker Verification},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
pages = {6036--6040},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICASSP.2019.8683245},
doi = {10.1109/ICASSP.2019.8683245},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/LiTSW19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ZhangL019,
author = {Yang Zhang and
Lantian Li and
Dong Wang},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {VAE-Based Regularization for Deep Speaker Embedding},
booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech
Communication Association, Graz, Austria, 15-19 September 2019},
pages = {4020--4024},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-2486},
doi = {10.21437/INTERSPEECH.2019-2486},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ZhangL019.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1904-03617,
author = {Yang Zhang and
Lantian Li and
Dong Wang},
title = {VAE-based regularization for deep speaker embedding},
journal = {CoRR},
volume = {abs/1904.03617},
year = {2019},
url = {http://arxiv.org/abs/1904.03617},
eprinttype = {arXiv},
eprint = {1904.03617},
timestamp = {Thu, 22 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1904-03617.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1907-07626,
author = {Zhiyuan Tang and
Dong Wang and
Liming Song},
title = {{AP19-OLR} Challenge: Three Tasks and Their Baselines},
journal = {CoRR},
volume = {abs/1907.07626},
year = {2019},
url = {http://arxiv.org/abs/1907.07626},
eprinttype = {arXiv},
eprint = {1907.07626},
timestamp = {Sat, 21 Sep 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1907-07626.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1908-10092,
author = {Xueyi Wang and
Lantian Li and
Dong Wang},
title = {VAE-based Domain Adaptation for Speaker Verification},
journal = {CoRR},
volume = {abs/1908.10092},
year = {2019},
url = {http://arxiv.org/abs/1908.10092},
eprinttype = {arXiv},
eprint = {1908.10092},
timestamp = {Fri, 24 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1908-10092.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-13288,
author = {Haoran Sun and
Yunqi Cai and
Lantian Li and
Dong Wang},
title = {On Investigation of Unsupervised Speech Factorization Based on Normalization
Flow},
journal = {CoRR},
volume = {abs/1910.13288},
year = {2019},
url = {http://arxiv.org/abs/1910.13288},
eprinttype = {arXiv},
eprint = {1910.13288},
timestamp = {Thu, 31 Oct 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-13288.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1911-01799,
author = {Yue Fan and
Jiawen Kang and
Lantian Li and
Kaicheng Li and
Haolin Chen and
Sitong Cheng and
Pengyuan Zhang and
Ziya Zhou and
Yunqi Cai and
Dong Wang},
title = {{CN-CELEB:} a challenging Chinese speaker recognition dataset},
journal = {CoRR},
volume = {abs/1911.01799},
year = {2019},
url = {http://arxiv.org/abs/1911.01799},
eprinttype = {arXiv},
eprint = {1911.01799},
timestamp = {Fri, 24 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1911-01799.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/TangWCLA18,
author = {Zhiyuan Tang and
Dong Wang and
Yixiang Chen and
Lantian Li and
Andrew Abel},
title = {Phonetic Temporal Neural Model for Language Identification},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {26},
number = {1},
pages = {134--144},
year = {2018},
url = {https://doi.org/10.1109/TASLP.2017.2764271},
doi = {10.1109/TASLP.2017.2764271},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/TangWCLA18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/ShiTLZ018,
author = {Ying Shi and
Zhiyuan Tang and
Lantian Li and
Zheling Zhang and
Dong Wang},
title = {Map and Relabel: Towards Almost-Zero Resource Speech Recognition},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2018, Honolulu, HI, USA, November
12-15, 2018},
pages = {591--595},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.23919/APSIPA.2018.8659508},
doi = {10.23919/APSIPA.2018.8659508},
timestamp = {Wed, 10 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/ShiTLZ018.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/TangWC18,
author = {Zhiyuan Tang and
Dong Wang and
Qing Chen},
title = {{AP18-OLR} Challenge: Three Tasks and Their Baselines},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2018, Honolulu, HI, USA, November
12-15, 2018},
pages = {596--600},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.23919/APSIPA.2018.8659714},
doi = {10.23919/APSIPA.2018.8659714},
timestamp = {Sat, 21 Sep 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/TangWC18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/ZhangZZW18,
author = {Jiyuan Zhang and
Zheling Zhang and
Shiyue Zhang and
Dong Wang},
title = {VV-Couplet: An open source Chinese couplet generation system},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2018, Honolulu, HI, USA, November
12-15, 2018},
pages = {1756--1760},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.23919/APSIPA.2018.8659474},
doi = {10.23919/APSIPA.2018.8659474},
timestamp = {Mon, 14 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/ZhangZZW18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ZhangKWLTD018,
author = {Miao Zhang and
Xiaofei Kang and
Yanqing Wang and
Lantian Li and
Zhiyuan Tang and
Haisheng Dai and
Dong Wang},
title = {Human and Machine Speaker Recognition Based on Short Trivial Events},
booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
pages = {5009--5013},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/ICASSP.2018.8462027},
doi = {10.1109/ICASSP.2018.8462027},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ZhangKWLTD018.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LiWCSTZ18,
author = {Lantian Li and
Dong Wang and
Yixiang Chen and
Ying Shi and
Zhiyuan Tang and
Thomas Fang Zheng},
title = {Deep Factorization for Speech Signal},
booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
pages = {5094--5098},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/ICASSP.2018.8462169},
doi = {10.1109/ICASSP.2018.8462169},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/LiWCSTZ18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LiTWZ18,
author = {Lantian Li and
Zhiyuan Tang and
Dong Wang and
Thomas Fang Zheng},
title = {Full-Info Training for Deep Speaker Feature Learning},
booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
pages = {5369--5373},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/ICASSP.2018.8461747},
doi = {10.1109/ICASSP.2018.8461747},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/LiTWZ18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iscslp/ZhangW18,
author = {Jiyuan Zhang and
Dong Wang},
title = {Chinese Poetry Generation with Flexible Styles},
booktitle = {11th International Symposium on Chinese Spoken Language Processing,
{ISCSLP} 2018, Taipei City, Taiwan, November 26-29, 2018},
pages = {419--423},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/ISCSLP.2018.8706636},
doi = {10.1109/ISCSLP.2018.8706636},
timestamp = {Mon, 14 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iscslp/ZhangW18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1803-00886,
author = {Lantian Li and
Dong Wang and
Yixiang Chen and
Ying Shi and
Zhiyuan Tang and
Thomas Fang Zheng},
title = {Deep factorization for speech signal},
journal = {CoRR},
volume = {abs/1803.00886},
year = {2018},
url = {http://arxiv.org/abs/1803.00886},
eprinttype = {arXiv},
eprint = {1803.00886},
timestamp = {Wed, 10 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1803-00886.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1806-00616,
author = {Zhiyuan Tang and
Dong Wang and
Qing Chen},
title = {{AP18-OLR} Challenge: Three Tasks and Their Baselines},
journal = {CoRR},
volume = {abs/1806.00616},
year = {2018},
url = {http://arxiv.org/abs/1806.00616},
eprinttype = {arXiv},
eprint = {1806.00616},
timestamp = {Sat, 09 Mar 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1806-00616.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1807-06500,
author = {Jiyuan Zhang and
Dong Wang},
title = {Chinese Poetry Generation with Flexible Styles},
journal = {CoRR},
volume = {abs/1807.06500},
year = {2018},
url = {http://arxiv.org/abs/1807.06500},
eprinttype = {arXiv},
eprint = {1807.06500},
timestamp = {Mon, 14 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1807-06500.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-03255,
author = {Lantian Li and
Zhiyuan Tang and
Ying Shi and
Dong Wang},
title = {Phonetic-attention scoring for deep speaker features in speaker verification},
journal = {CoRR},
volume = {abs/1811.03255},
year = {2018},
url = {http://arxiv.org/abs/1811.03255},
eprinttype = {arXiv},
eprint = {1811.03255},
timestamp = {Wed, 10 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-03255.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-03258,
author = {Lantian Li and
Zhiyuan Tang and
Ying Shi and
Dong Wang},
title = {Gaussian-Constrained training for speaker verification},
journal = {CoRR},
volume = {abs/1811.03258},
year = {2018},
url = {http://arxiv.org/abs/1811.03258},
eprinttype = {arXiv},
eprint = {1811.03258},
timestamp = {Wed, 10 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-03258.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/TangLWV17,
author = {Zhiyuan Tang and
Lantian Li and
Dong Wang and
Ravichander Vipperla},
title = {Collaborative Joint Training With Multitask Recurrent Model for Speech
and Speaker Recognition},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {25},
number = {3},
pages = {493--504},
year = {2017},
url = {https://doi.org/10.1109/TASLP.2016.2639323},
doi = {10.1109/TASLP.2016.2639323},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/TangLWV17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/ZhangFWWAZZ17,
author = {Jiyuan Zhang and
Yang Feng and
Dong Wang and
Yang Wang and
Andrew Abel and
Shiyue Zhang and
Andi Zhang},
editor = {Regina Barzilay and
Min{-}Yen Kan},
title = {Flexible and Creative Chinese Poetry Generation Using Neural Memory},
booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational
Linguistics, {ACL} 2017, Vancouver, Canada, July 30 - August 4, Volume
1: Long Papers},
pages = {1364--1373},
publisher = {Association for Computational Linguistics},
year = {2017},
url = {https://doi.org/10.18653/v1/P17-1125},
doi = {10.18653/V1/P17-1125},
timestamp = {Tue, 29 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/acl/ZhangFWWAZZ17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/0013LTZ17,
author = {Dong Wang and
Lantian Li and
Zhiyuan Tang and
Thomas Fang Zheng},
title = {Deep speaker verification: Do we need end to end?},
booktitle = {2017 Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2017, Kuala Lumpur, Malaysia,
December 12-15, 2017},
pages = {177--181},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/APSIPA.2017.8282024},
doi = {10.1109/APSIPA.2017.8282024},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/0013LTZ17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/ZhangCLW17,
author = {Miao Zhang and
Yixiang Chen and
Lantian Li and
Dong Wang},
title = {Speaker recognition with cough, laugh and "Wei"},
booktitle = {2017 Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2017, Kuala Lumpur, Malaysia,
December 12-15, 2017},
pages = {497--501},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/APSIPA.2017.8282083},
doi = {10.1109/APSIPA.2017.8282083},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/ZhangCLW17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/ShiHTWZ17,
author = {Ying Shi and
Askar Hamdullah and
Zhiyuan Tang and
Dong Wang and
Thomas Fang Zheng},
title = {A free Kazakh speech database and a speech recognition baseline},
booktitle = {2017 Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2017, Kuala Lumpur, Malaysia,
December 12-15, 2017},
pages = {745--748},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/APSIPA.2017.8282133},
doi = {10.1109/APSIPA.2017.8282133},
timestamp = {Wed, 10 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/ShiHTWZ17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/TangWCC17,
author = {Zhiyuan Tang and
Dong Wang and
Yixiang Chen and
Qing Chen},
title = {{AP17-OLR} challenge: Data, plan, and baseline},
booktitle = {2017 Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2017, Kuala Lumpur, Malaysia,
December 12-15, 2017},
pages = {749--753},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/APSIPA.2017.8282134},
doi = {10.1109/APSIPA.2017.8282134},
timestamp = {Sat, 09 Mar 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/TangWCC17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/LiWRZ17,
author = {Lantian Li and
Dong Wang and
Askar Rozi and
Thomas Fang Zheng},
title = {Cross-lingual speaker verification with deep feature learning},
booktitle = {2017 Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2017, Kuala Lumpur, Malaysia,
December 12-15, 2017},
pages = {1040--1044},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/APSIPA.2017.8282182},
doi = {10.1109/APSIPA.2017.8282182},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/LiWRZ17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/ZhangMWH17,
author = {Shiyue Zhang and
Gulnigar Mahmut and
Dong Wang and
Askar Hamdulla},
title = {Memory-augmented Chinese-Uyghur neural machine translation},
booktitle = {2017 Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2017, Kuala Lumpur, Malaysia,
December 12-15, 2017},
pages = {1092--1096},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/APSIPA.2017.8282190},
doi = {10.1109/APSIPA.2017.8282190},
timestamp = {Wed, 10 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/ZhangMWH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/FengZZWA17,
author = {Yang Feng and
Shiyue Zhang and
Andi Zhang and
Dong Wang and
Andrew Abel},
editor = {Martha Palmer and
Rebecca Hwa and
Sebastian Riedel},
title = {Memory-augmented Neural Machine Translation},
booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural
Language Processing, {EMNLP} 2017, Copenhagen, Denmark, September
9-11, 2017},
pages = {1390--1399},
publisher = {Association for Computational Linguistics},
year = {2017},
url = {https://doi.org/10.18653/v1/d17-1146},
doi = {10.18653/V1/D17-1146},
timestamp = {Tue, 29 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/emnlp/FengZZWA17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TangSWFZ17,
author = {Zhiyuan Tang and
Ying Shi and
Dong Wang and
Yang Feng and
Shiyue Zhang},
title = {Memory visualization for gated recurrent neural networks in speech
recognition},
booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017},
pages = {2736--2740},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/ICASSP.2017.7952654},
doi = {10.1109/ICASSP.2017.7952654},
timestamp = {Wed, 10 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/TangSWFZ17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiCWZ17,
author = {Lantian Li and
Yixiang Chen and
Dong Wang and
Thomas Fang Zheng},
editor = {Francisco Lacerda},
title = {A Study on Replay Attack and Anti-Spoofing for Automatic Speaker Verification},
booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech
Communication Association, Stockholm, Sweden, August 20-24, 2017},
pages = {92--96},
publisher = {{ISCA}},
year = {2017},
url = {https://doi.org/10.21437/Interspeech.2017-456},
doi = {10.21437/INTERSPEECH.2017-456},
timestamp = {Sun, 06 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiCWZ17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiCSTW17,
author = {Lantian Li and
Yixiang Chen and
Ying Shi and
Zhiyuan Tang and
Dong Wang},
editor = {Francisco Lacerda},
title = {Deep Speaker Feature Learning for Text-Independent Speaker Verification},
booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech
Communication Association, Stockholm, Sweden, August 20-24, 2017},
pages = {1542--1546},
publisher = {{ISCA}},
year = {2017},
url = {https://doi.org/10.21437/Interspeech.2017-452},
doi = {10.21437/INTERSPEECH.2017-452},
timestamp = {Sun, 06 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiCSTW17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ococosda/TangWCSL17,
author = {Zhiyuan Tang and
Dong Wang and
Yixiang Chen and
Ying Shi and
Lantian Li},
title = {Phone-aware neural language identification},
booktitle = {20th Conference of the Oriental Chapter of the International Coordinating
Committee on Speech Databases and Speech {I/O} Systems and Assessment,
{O-COCOSDA} 2017, Seoul, South Korea, November 1-3, 2017},
pages = {1--6},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/ICSDA.2017.8384445},
doi = {10.1109/ICSDA.2017.8384445},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ococosda/TangWCSL17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ococosda/WangZTSLZYLXHAM17,
author = {Dong Wang and
Thomas Fang Zheng and
Zhiyuan Tang and
Ying Shi and
Lantian Li and
Shiyue Zhang and
Hongzhi Yu and
Guanyu Li and
Shipeng Xu and
Askar Hamdulla and
Mijit Ablimit and
Gulnigar Mahmut},
title = {{M2ASR:} Ambitions and first year progress},
booktitle = {20th Conference of the Oriental Chapter of the International Coordinating
Committee on Speech Databases and Speech {I/O} Systems and Assessment,
{O-COCOSDA} 2017, Seoul, South Korea, November 1-3, 2017},
pages = {1--6},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/ICSDA.2017.8384469},
doi = {10.1109/ICSDA.2017.8384469},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ococosda/WangZTSLZYLXHAM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/TangWCLA17,
author = {Zhiyuan Tang and
Dong Wang and
Yixiang Chen and
Lantian Li and
Andrew Abel},
title = {Phonetic Temporal Neural Model for Language Identification},
journal = {CoRR},
volume = {abs/1705.03151},
year = {2017},
url = {http://arxiv.org/abs/1705.03151},
eprinttype = {arXiv},
eprint = {1705.03151},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/TangWCLA17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/TangWCSL17,
author = {Zhiyuan Tang and
Dong Wang and
Yixiang Chen and
Ying Shi and
Lantian Li},
title = {Phone-aware Neural Language Identification},
journal = {CoRR},
volume = {abs/1705.03152},
year = {2017},
url = {http://arxiv.org/abs/1705.03152},
eprinttype = {arXiv},
eprint = {1705.03152},
timestamp = {Wed, 10 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/TangWCSL17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LiCSTW17,
author = {Lantian Li and
Yixiang Chen and
Ying Shi and
Zhiyuan Tang and
Dong Wang},
title = {Deep Speaker Feature Learning for Text-independent Speaker Verification},
journal = {CoRR},
volume = {abs/1705.03670},
year = {2017},
url = {http://arxiv.org/abs/1705.03670},
eprinttype = {arXiv},
eprint = {1705.03670},
timestamp = {Wed, 10 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/LiCSTW17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ZhangFWWAZZ17,
author = {Jiyuan Zhang and
Yang Feng and
Dong Wang and
Yang Wang and
Andrew Abel and
Shiyue Zhang and
Andi Zhang},
title = {Flexible and Creative Chinese Poetry Generation Using Neural Memory},
journal = {CoRR},
volume = {abs/1705.03773},
year = {2017},
url = {http://arxiv.org/abs/1705.03773},
eprinttype = {arXiv},
eprint = {1705.03773},
timestamp = {Tue, 29 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/ZhangFWWAZZ17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WangLSCT17,
author = {Dong Wang and
Lantian Li and
Ying Shi and
Yixiang Chen and
Zhiyuan Tang},
title = {Deep Factorization for Speech Signal},
journal = {CoRR},
volume = {abs/1706.01777},
year = {2017},
url = {http://arxiv.org/abs/1706.01777},
eprinttype = {arXiv},
eprint = {1706.01777},
timestamp = {Wed, 10 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/WangLSCT17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LiCWZ17,
author = {Lantian Li and
Yixiang Chen and
Dong Wang and
Thomas Fang Zheng},
title = {A Study on Replay Attack and Anti-Spoofing for Automatic Speaker Verification},
journal = {CoRR},
volume = {abs/1706.02101},
year = {2017},
url = {http://arxiv.org/abs/1706.02101},
eprinttype = {arXiv},
eprint = {1706.02101},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LiCWZ17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WangLTZ17,
author = {Dong Wang and
Lantian Li and
Zhiyuan Tang and
Thomas Fang Zheng},
title = {Deep Speaker Verification: Do We Need End to End?},
journal = {CoRR},
volume = {abs/1706.07859},
year = {2017},
url = {http://arxiv.org/abs/1706.07859},
eprinttype = {arXiv},
eprint = {1706.07859},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/WangLTZ17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ZhangCLW17,
author = {Miao Zhang and
Yixiang Chen and
Lantian Li and
Dong Wang},
title = {Speaker Recognition with Cough, Laugh and "Wei"},
journal = {CoRR},
volume = {abs/1706.07860},
year = {2017},
url = {http://arxiv.org/abs/1706.07860},
eprinttype = {arXiv},
eprint = {1706.07860},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/ZhangCLW17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LiWRZ17,
author = {Lantian Li and
Dong Wang and
Askar Rozi and
Thomas Fang Zheng},
title = {Cross-lingual Speaker Verification with Deep Feature Learning},
journal = {CoRR},
volume = {abs/1706.07861},
year = {2017},
url = {http://arxiv.org/abs/1706.07861},
eprinttype = {arXiv},
eprint = {1706.07861},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LiWRZ17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ZhangMWH17,
author = {Shiyue Zhang and
Gulnigar Mahmut and
Dong Wang and
Askar Hamdulla},
title = {Memory-augmented Chinese-Uyghur Neural Machine Translation},
journal = {CoRR},
volume = {abs/1706.08683},
year = {2017},
url = {http://arxiv.org/abs/1706.08683},
eprinttype = {arXiv},
eprint = {1706.08683},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/ZhangMWH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/TangWCC17,
author = {Zhiyuan Tang and
Dong Wang and
Yixiang Chen and
Qing Chen},
title = {{AP17-OLR} Challenge: Data, Plan, and Baseline},
journal = {CoRR},
volume = {abs/1706.09742},
year = {2017},
url = {http://arxiv.org/abs/1706.09742},
eprinttype = {arXiv},
eprint = {1706.09742},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/TangWCC17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1708-02005,
author = {Yang Feng and
Shiyue Zhang and
Andi Zhang and
Dong Wang and
Andrew Abel},
title = {Memory-augmented Neural Machine Translation},
journal = {CoRR},
volume = {abs/1708.02005},
year = {2017},
url = {http://arxiv.org/abs/1708.02005},
eprinttype = {arXiv},
eprint = {1708.02005},
timestamp = {Tue, 29 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1708-02005.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1710-01789,
author = {Aodong Li and
Shiyue Zhang and
Dong Wang and
Thomas Fang Zheng},
title = {Enhanced Neural Machine Translation by Learning from Draft},
journal = {CoRR},
volume = {abs/1710.01789},
year = {2017},
url = {http://arxiv.org/abs/1710.01789},
eprinttype = {arXiv},
eprint = {1710.01789},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1710-01789.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1711-00366,
author = {Lantian Li and
Zhiyuan Tang and
Dong Wang},
title = {Full-info Training for Deep Speaker Feature Learning},
journal = {CoRR},
volume = {abs/1711.00366},
year = {2017},
url = {http://arxiv.org/abs/1711.00366},
eprinttype = {arXiv},
eprint = {1711.00366},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1711-00366.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1711-04329,
author = {Shiyue Zhang and
Pengtao Xie and
Dong Wang and
Eric P. Xing},
title = {Medical Diagnosis From Laboratory Tests by Combining Generative and
Discriminative Learning},
journal = {CoRR},
volume = {abs/1711.04329},
year = {2017},
url = {http://arxiv.org/abs/1711.04329},
eprinttype = {arXiv},
eprint = {1711.04329},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1711-04329.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1711-05443,
author = {Miao Zhang and
Xiaofei Kang and
Yanqing Wang and
Lantian Li and
Zhiyuan Tang and
Haisheng Dai and
Dong Wang},
title = {Human and Machine Speaker Recognition Based on Short Trivial Events},
journal = {CoRR},
volume = {abs/1711.05443},
year = {2017},
url = {http://arxiv.org/abs/1711.05443},
eprinttype = {arXiv},
eprint = {1711.05443},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1711-05443.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/LiWZZ16,
author = {Lantian Li and
Dong Wang and
Chenhao Zhang and
Thomas Fang Zheng},
title = {Improving Short Utterance Speaker Recognition by Modeling Speech Unit
Classes},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {24},
number = {6},
pages = {1129--1139},
year = {2016},
url = {https://doi.org/10.1109/TASLP.2016.2544660},
doi = {10.1109/TASLP.2016.2544660},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/LiWZZ16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/MaWT16,
author = {Xi Ma and
Dong Wang and
Javier Tejedor},
title = {Similar Word Model for Unfrequent Word Enhancement in Speech Recognition},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {24},
number = {10},
pages = {1819--1830},
year = {2016},
url = {https://doi.org/10.1109/TASLP.2016.2585863},
doi = {10.1109/TASLP.2016.2585863},
timestamp = {Mon, 03 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/MaWT16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/LiWZZJ16,
author = {Lantian Li and
Dong Wang and
Xiaodong Zhang and
Thomas Fang Zheng and
Panshi Jin},
title = {System combination for short utterance speaker recognition},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2016, Jeju, South Korea, December
13-16, 2016},
pages = {1--5},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/APSIPA.2016.7820903},
doi = {10.1109/APSIPA.2016.7820903},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/LiWZZJ16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/LiuXFW16,
author = {Aiting Liu and
Chao Xing and
Yang Feng and
Dong Wang},
title = {Learning ordered word representations with {\(\gamma\)}-decay dropout},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2016, Jeju, South Korea, December
13-16, 2016},
pages = {1--5},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/APSIPA.2016.7820839},
doi = {10.1109/APSIPA.2016.7820839},
timestamp = {Fri, 29 Nov 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/LiuXFW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/RoziLWZ16,
author = {Askar Rozi and
Lantian Li and
Dong Wang and
Thomas Fang Zheng},
title = {Feature transformation for speaker verification under speaking rate
mismatch condition},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2016, Jeju, South Korea, December
13-16, 2016},
pages = {1--4},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/APSIPA.2016.7820824},
doi = {10.1109/APSIPA.2016.7820824},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/RoziLWZ16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/TangLW16,
author = {Zhiyuan Tang and
Lantian Li and
Dong Wang},
title = {Multi-task recurrent model for speech and speaker recognition},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2016, Jeju, South Korea, December
13-16, 2016},
pages = {1--4},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/APSIPA.2016.7820893},
doi = {10.1109/APSIPA.2016.7820893},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/TangLW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/TangLW16a,
author = {Zhiyuan Tang and
Lantian Li and
Dong Wang},
title = {Multi-task recurrent model for true multilingual speech recognition},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2016, Jeju, South Korea, December
13-16, 2016},
pages = {1--4},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/APSIPA.2016.7820821},
doi = {10.1109/APSIPA.2016.7820821},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/TangLW16a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/WangLTC16,
author = {Dong Wang and
Lantian Li and
Difei Tang and
Qing Chen},
title = {{AP16-OL7:} {A} multilingual database for oriental languages and a
language recognition baseline},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2016, Jeju, South Korea, December
13-16, 2016},
pages = {1--5},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/APSIPA.2016.7820796},
doi = {10.1109/APSIPA.2016.7820796},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/WangLTC16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/bics/WangLW16,
author = {Qixin Wang and
Tianyi Luo and
Dong Wang},
editor = {Cheng{-}Lin Liu and
Amir Hussain and
Bin Luo and
Kay Chen Tan and
Yi Zeng and
Zhaoxiang Zhang},
title = {Can Machine Generate Traditional Chinese Poetry? {A} Feigenbaum Test},
booktitle = {Advances in Brain Inspired Cognitive Systems - 8th International Conference,
{BICS} 2016, Beijing, China, November 28-30, 2016, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {10023},
pages = {34--46},
year = {2016},
url = {https://doi.org/10.1007/978-3-319-49685-6\_4},
doi = {10.1007/978-3-319-49685-6\_4},
timestamp = {Tue, 26 Mar 2024 13:26:54 +0100},
biburl = {https://dblp.org/rec/conf/bics/WangLW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TangWZ16,
author = {Zhiyuan Tang and
Dong Wang and
Zhiyong Zhang},
title = {Recurrent neural network training with dark knowledge transfer},
booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016},
pages = {5900--5904},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/ICASSP.2016.7472809},
doi = {10.1109/ICASSP.2016.7472809},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/TangWZ16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/WangLWX16,
author = {Qixin Wang and
Tianyi Luo and
Dong Wang and
Chao Xing},
editor = {Subbarao Kambhampati},
title = {Chinese Song Iambics Generation with Neural Attention-Based Model},
booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI} 2016, New York, NY, USA, 9-15 July
2016},
pages = {2943--2949},
publisher = {{IJCAI/AAAI} Press},
year = {2016},
url = {http://www.ijcai.org/Abstract/16/418},
timestamp = {Tue, 20 Aug 2019 16:19:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/WangLWX16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iscslp/LiWXZ16,
author = {Lantian Li and
Dong Wang and
Chao Xing and
Thomas Fang Zheng},
title = {Max-margin metric learning for speaker recognition},
booktitle = {10th International Symposium on Chinese Spoken Language Processing,
{ISCSLP} 2016, Tianjin, China, October 17-20, 2016},
pages = {1--4},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/ISCSLP.2016.7918380},
doi = {10.1109/ISCSLP.2016.7918380},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iscslp/LiWXZ16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iscslp/LiXWYZ16,
author = {Lantian Li and
Chao Xing and
Dong Wang and
Kaimin Yu and
Thomas Fang Zheng},
title = {Binary speaker embedding},
booktitle = {10th International Symposium on Chinese Spoken Language Processing,
{ISCSLP} 2016, Tianjin, China, October 17-20, 2016},
pages = {1--4},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/ISCSLP.2016.7918381},
doi = {10.1109/ISCSLP.2016.7918381},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iscslp/LiXWYZ16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nlpcc/ZhangLW16,
author = {Dongxu Zhang and
Tianyi Luo and
Dong Wang},
editor = {Chin{-}Yew Lin and
Nianwen Xue and
Dongyan Zhao and
Xuanjing Huang and
Yansong Feng},
title = {Learning from {LDA} Using Deep Neural Networks},
booktitle = {Natural Language Understanding and Intelligent Applications - 5th
{CCF} Conference on Natural Language Processing and Chinese Computing,
{NLPCC} 2016, and 24th International Conference on Computer Processing
of Oriental Languages, {ICCPOL} 2016, Kunming, China, December 2-6,
2016, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {10102},
pages = {657--664},
publisher = {Springer},
year = {2016},
url = {https://doi.org/10.1007/978-3-319-50496-4\_59},
doi = {10.1007/978-3-319-50496-4\_59},
timestamp = {Fri, 16 Feb 2024 08:27:36 +0100},
biburl = {https://dblp.org/rec/conf/nlpcc/ZhangLW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nlpcc/ZhangW16,
author = {Dongxu Zhang and
Dong Wang},
editor = {Chin{-}Yew Lin and
Nianwen Xue and
Dongyan Zhao and
Xuanjing Huang and
Yansong Feng},
title = {Relation Classification: {CNN} or RNN?},
booktitle = {Natural Language Understanding and Intelligent Applications - 5th
{CCF} Conference on Natural Language Processing and Chinese Computing,
{NLPCC} 2016, and 24th International Conference on Computer Processing
of Oriental Languages, {ICCPOL} 2016, Kunming, China, December 2-6,
2016, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {10102},
pages = {665--675},
publisher = {Springer},
year = {2016},
url = {https://doi.org/10.1007/978-3-319-50496-4\_60},
doi = {10.1007/978-3-319-50496-4\_60},
timestamp = {Fri, 04 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nlpcc/ZhangW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LiWZ16,
author = {Lantian Li and
Dong Wang and
Thomas Fang Zheng},
title = {System Combination for Short Utterance Speaker Recognition},
journal = {CoRR},
volume = {abs/1603.09460},
year = {2016},
url = {http://arxiv.org/abs/1603.09460},
eprinttype = {arXiv},
eprint = {1603.09460},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LiWZ16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/TangLW16,
author = {Zhiyuan Tang and
Lantian Li and
Dong Wang},
title = {Multi-task Recurrent Model for Speech and Speaker Recognition},
journal = {CoRR},
volume = {abs/1603.09643},
year = {2016},
url = {http://arxiv.org/abs/1603.09643},
eprinttype = {arXiv},
eprint = {1603.09643},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/TangLW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WangLWX16,
author = {Qixin Wang and
Tianyi Luo and
Dong Wang and
Chao Xing},
title = {Chinese Song Iambics Generation with Neural Attention-based Model},
journal = {CoRR},
volume = {abs/1604.06274},
year = {2016},
url = {http://arxiv.org/abs/1604.06274},
eprinttype = {arXiv},
eprint = {1604.06274},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/WangLWX16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WangLW16,
author = {Qixin Wang and
Tianyi Luo and
Dong Wang},
title = {Can Machine Generate Traditional Chinese Poetry? {A} Feigenbaum Test},
journal = {CoRR},
volume = {abs/1606.05829},
year = {2016},
url = {http://arxiv.org/abs/1606.05829},
eprinttype = {arXiv},
eprint = {1606.05829},
timestamp = {Thu, 05 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/WangLW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/TangLW16a,
author = {Zhiyuan Tang and
Lantian Li and
Dong Wang},
title = {Multi-task Recurrent Model for True Multilingual Speech Recognition},
journal = {CoRR},
volume = {abs/1609.08337},
year = {2016},
url = {http://arxiv.org/abs/1609.08337},
eprinttype = {arXiv},
eprint = {1609.08337},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/TangLW16a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WangTTC16,
author = {Dong Wang and
Zhiyuan Tang and
Difei Tang and
Qing Chen},
title = {{OC16-CE80:} {A} Chinese-English Mixlingual Database and {A} Speech
Recognition Baseline},
journal = {CoRR},
volume = {abs/1609.08412},
year = {2016},
url = {http://arxiv.org/abs/1609.08412},
eprinttype = {arXiv},
eprint = {1609.08412},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/WangTTC16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ZhaoLWP16,
author = {Chenghui Zhao and
Lantian Li and
Dong Wang and
April Pu},
title = {Local Training for {PLDA} in Speaker Verification},
journal = {CoRR},
volume = {abs/1609.08433},
year = {2016},
url = {http://arxiv.org/abs/1609.08433},
eprinttype = {arXiv},
eprint = {1609.08433},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/ZhaoLWP16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LiCWZ16,
author = {Lantian Li and
Yixiang Chen and
Dong Wang and
Chenghui Zhao},
title = {Weakly Supervised {PLDA} Training},
journal = {CoRR},
volume = {abs/1609.08441},
year = {2016},
url = {http://arxiv.org/abs/1609.08441},
eprinttype = {arXiv},
eprint = {1609.08441},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LiCWZ16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LiTWFZ16,
author = {Lantian Li and
Zhiyuan Tang and
Dong Wang and
Yang Feng and
Shiyue Zhang},
title = {Collaborative Learning for Language and Speaker Recognition},
journal = {CoRR},
volume = {abs/1609.08442},
year = {2016},
url = {http://arxiv.org/abs/1609.08442},
eprinttype = {arXiv},
eprint = {1609.08442},
timestamp = {Fri, 29 Nov 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/LiTWFZ16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WangLTC16,
author = {Dong Wang and
Lantian Li and
Difei Tang and
Qing Chen},
title = {{AP16-OL7:} {A} Multilingual Database for Oriental Languages and {A}
Language Recognition Baseline},
journal = {CoRR},
volume = {abs/1609.08445},
year = {2016},
url = {http://arxiv.org/abs/1609.08445},
eprinttype = {arXiv},
eprint = {1609.08445},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/WangLTC16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/TangSWFZ16,
author = {Zhiyuan Tang and
Ying Shi and
Dong Wang and
Yang Feng and
Shiyue Zhang},
title = {Memory Visualization for Gated Recurrent Neural Networks in Speech
Recognition},
journal = {CoRR},
volume = {abs/1609.08789},
year = {2016},
url = {http://arxiv.org/abs/1609.08789},
eprinttype = {arXiv},
eprint = {1609.08789},
timestamp = {Wed, 10 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/TangSWFZ16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ejasmp/YinLZLWTZL15,
author = {Shi Yin and
Chao Liu and
Zhiyong Zhang and
Yiye Lin and
Dong Wang and
Javier Tejedor and
Thomas Fang Zheng and
Yinguo Li},
title = {Noisy training for deep neural networks in speech recognition},
journal = {{EURASIP} J. Audio Speech Music. Process.},
volume = {2015},
pages = {2},
year = {2015},
url = {https://doi.org/10.1186/s13636-014-0047-0},
doi = {10.1186/S13636-014-0047-0},
timestamp = {Mon, 03 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ejasmp/YinLZLWTZL15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/BieWWZ15,
author = {Fanhu Bie and
Dong Wang and
Jun Wang and
Thomas Fang Zheng},
title = {Detection and reconstruction of clipped speech for speaker recognition},
journal = {Speech Commun.},
volume = {72},
pages = {218--231},
year = {2015},
url = {https://doi.org/10.1016/j.specom.2015.06.008},
doi = {10.1016/J.SPECOM.2015.06.008},
timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/speech/BieWWZ15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl-cvsc/ZhangYWL15,
author = {Dongxu Zhang and
Bin Yuan and
Dong Wang and
Rong Liu},
editor = {Alexandre Allauzen and
Edward Grefenstette and
Karl Moritz Hermann and
Hugo Larochelle and
Scott Wen{-}tau Yih},
title = {Joint Semantic Relevance Learning with Text Data and Graph Knowledge},
booktitle = {Proceedings of the 3rd Workshop on Continuous Vector Space Models
and their Compositionality, {CVSC} 2015, Beijing, China, July 26-31,
2015},
pages = {32--40},
publisher = {Association for Computational Linguistics},
year = {2015},
url = {https://doi.org/10.18653/v1/W15-4004},
doi = {10.18653/V1/W15-4004},
timestamp = {Fri, 04 Nov 2022 18:37:50 +0100},
biburl = {https://dblp.org/rec/conf/acl-cvsc/ZhangYWL15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/PanXW15,
author = {Yiqiao Pan and
Chao Xing and
Dong Wang},
title = {Document classification with spherical word vectors},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2015, Hong Kong, December 16-19, 2015},
pages = {270--273},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/APSIPA.2015.7415518},
doi = {10.1109/APSIPA.2015.7415518},
timestamp = {Wed, 16 Oct 2019 14:14:55 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/PanXW15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/ZhaoWZZ15,
author = {Mengyuan Zhao and
Dong Wang and
Zhiyong Zhang and
Xuewei Zhang},
title = {Music removal by convolutional denoising autoencoder in speech recognition},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2015, Hong Kong, December 16-19, 2015},
pages = {338--341},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/APSIPA.2015.7415289},
doi = {10.1109/APSIPA.2015.7415289},
timestamp = {Fri, 09 Feb 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/ZhaoWZZ15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/LiLZW15,
author = {Lantian Li and
Yiye Lin and
Zhiyong Zhang and
Dong Wang},
title = {Improved deep speaker feature learning for text-dependent speaker
recognition},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2015, Hong Kong, December 16-19, 2015},
pages = {426--429},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/APSIPA.2015.7415306},
doi = {10.1109/APSIPA.2015.7415306},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/LiLZW15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/WangZ15,
author = {Dong Wang and
Thomas Fang Zheng},
title = {Transfer learning for speech and language processing},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2015, Hong Kong, December 16-19, 2015},
pages = {1225--1237},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/APSIPA.2015.7415532},
doi = {10.1109/APSIPA.2015.7415532},
timestamp = {Tue, 06 Feb 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/WangZ15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/chinasip/AskarWBWZ15,
author = {Rozi Askar and
Dong Wang and
Fanhu Bie and
Jun Wang and
Thomas Fang Zheng},
title = {Cross-lingual speaker verification based on linear transform},
booktitle = {{IEEE} China Summit and International Conference on Signal and Information
Processing, ChinaSIP 2015, Chengdu, China, July 12-15, 2015},
pages = {519--523},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ChinaSIP.2015.7230457},
doi = {10.1109/CHINASIP.2015.7230457},
timestamp = {Sun, 22 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/chinasip/AskarWBWZ15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/LuoWLP15,
author = {Tianyi Luo and
Dong Wang and
Rong Liu and
Yiqiao Pan},
editor = {Llu{\'{\i}}s M{\`{a}}rquez and
Chris Callison{-}Burch and
Jian Su and
Daniele Pighin and
Yuval Marton},
title = {Stochastic Top-k ListNet},
booktitle = {Proceedings of the 2015 Conference on Empirical Methods in Natural
Language Processing, {EMNLP} 2015, Lisbon, Portugal, September 17-21,
2015},
pages = {676--684},
publisher = {The Association for Computational Linguistics},
year = {2015},
url = {https://doi.org/10.18653/v1/d15-1079},
doi = {10.18653/V1/D15-1079},
timestamp = {Fri, 04 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/emnlp/LuoWLP15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ZhangLW15,
author = {Xuewei Zhang and
Yiye Lin and
Dong Wang},
title = {Lasso-based reverberation suppression in automatic speech Recognition},
booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia,
April 19-24, 2015},
pages = {5034--5037},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ICASSP.2015.7178929},
doi = {10.1109/ICASSP.2015.7178929},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ZhangLW15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/MaWWZ15,
author = {Xi Ma and
Xiaoxi Wang and
Dong Wang and
Zhiyong Zhang},
title = {Recognize foreign low-frequency words with similar pairs},
booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech
Communication Association, Dresden, Germany, September 6-10, 2015},
pages = {458--462},
publisher = {{ISCA}},
year = {2015},
url = {https://doi.org/10.21437/Interspeech.2015-175},
doi = {10.21437/INTERSPEECH.2015-175},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/MaWWZ15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ZengYW15,
author = {Xiangyu Zeng and
Shi Yin and
Dong Wang},
title = {Learning speech rate in speech recognition},
booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech
Communication Association, Dresden, Germany, September 6-10, 2015},
pages = {528--532},
publisher = {{ISCA}},
year = {2015},
url = {https://doi.org/10.21437/Interspeech.2015-197},
doi = {10.21437/INTERSPEECH.2015-197},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ZengYW15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/naacl/XingWLL15,
author = {Chao Xing and
Dong Wang and
Chao Liu and
Yiye Lin},
editor = {Rada Mihalcea and
Joyce Yue Chai and
Anoop Sarkar},
title = {Normalized Word Embedding and Orthogonal Transform for Bilingual Word
Translation},
booktitle = {{NAACL} {HLT} 2015, The 2015 Conference of the North American Chapter
of the Association for Computational Linguistics: Human Language Technologies,
Denver, Colorado, USA, May 31 - June 5, 2015},
pages = {1006--1011},
publisher = {The Association for Computational Linguistics},
year = {2015},
url = {https://doi.org/10.3115/v1/n15-1104},
doi = {10.3115/V1/N15-1104},
timestamp = {Fri, 06 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/naacl/XingWLL15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ococosda/RoziWZZ15,
author = {Askar Rozi and
Dong Wang and
Zhiyong Zhang and
Thomas Fang Zheng},
title = {An open/free database and Benchmark for Uyghur speaker recognition},
booktitle = {2015 International Conference Oriental {COCOSDA} held jointly with
2015 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE),
Shanghai, China, October 28-30, 2015},
pages = {81--85},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ICSDA.2015.7357869},
doi = {10.1109/ICSDA.2015.7357869},
timestamp = {Wed, 16 Oct 2019 14:14:56 +0200},
biburl = {https://dblp.org/rec/conf/ococosda/RoziWZZ15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WangLTZZ15,
author = {Dong Wang and
Chao Liu and
Zhiyuan Tang and
Zhiyong Zhang and
Mengyuan Zhao},
title = {Recurrent Neural Network Training with Dark Knowledge Transfer},
journal = {CoRR},
volume = {abs/1505.04630},
year = {2015},
url = {http://arxiv.org/abs/1505.04630},
eprinttype = {arXiv},
eprint = {1505.04630},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/WangLTZZ15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LiWZZ15b,
author = {Lantian Li and
Dong Wang and
Zhiyong Zhang and
Thomas Fang Zheng},
title = {Deep Speaker Vectors for Semi Text-independent Speaker Verification},
journal = {CoRR},
volume = {abs/1505.06427},
year = {2015},
url = {http://arxiv.org/abs/1505.06427},
eprinttype = {arXiv},
eprint = {1505.06427},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LiWZZ15b.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ZengYW15,
author = {Xiangyu Zeng and
Shi Yin and
Dong Wang},
title = {Learning Speech Rate in Speech Recognition},
journal = {CoRR},
volume = {abs/1506.00799},
year = {2015},
url = {http://arxiv.org/abs/1506.00799},
eprinttype = {arXiv},
eprint = {1506.00799},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/ZengYW15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/TangWPZ15,
author = {Zhiyuan Tang and
Dong Wang and
Yiqiao Pan and
Zhiyong Zhang},
title = {Knowledge Transfer Pre-training},
journal = {CoRR},
volume = {abs/1506.02256},
year = {2015},
url = {http://arxiv.org/abs/1506.02256},
eprinttype = {arXiv},
eprint = {1506.02256},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/TangWPZ15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/MaWWZ15,
author = {Xi Ma and
Xiaoxi Wang and
Dong Wang and
Zhiyong Zhang},
title = {Recognize Foreign Low-Frequency Words with Similar Pairs},
journal = {CoRR},
volume = {abs/1506.04940},
year = {2015},
url = {http://arxiv.org/abs/1506.04940},
eprinttype = {arXiv},
eprint = {1506.04940},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/MaWWZ15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LiLZW15,
author = {Lantian Li and
Yiye Lin and
Zhiyong Zhang and
Dong Wang},
title = {Improved Deep Speaker Feature Learning for Text-Dependent Speaker
Recognition},
journal = {CoRR},
volume = {abs/1506.08349},
year = {2015},
url = {http://arxiv.org/abs/1506.08349},
eprinttype = {arXiv},
eprint = {1506.08349},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LiLZW15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ZhangW15a,
author = {Dongxu Zhang and
Dong Wang},
title = {Relation Classification via Recurrent Neural Network},
journal = {CoRR},
volume = {abs/1508.01006},
year = {2015},
url = {http://arxiv.org/abs/1508.01006},
eprinttype = {arXiv},
eprint = {1508.01006},
timestamp = {Fri, 04 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/ZhangW15a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ZhangLWL15,
author = {Dongxu Zhang and
Tianyi Luo and
Dong Wang and
Rong Liu},
title = {Learning from {LDA} using Deep Neural Networks},
journal = {CoRR},
volume = {abs/1508.01011},
year = {2015},
url = {http://arxiv.org/abs/1508.01011},
eprinttype = {arXiv},
eprint = {1508.01011},
timestamp = {Fri, 04 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/ZhangLWL15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LiWXYZ15,
author = {Lantian Li and
Dong Wang and
Chao Xing and
Kaimin Yu and
Thomas Fang Zheng},
title = {Binary Speaker Embedding},
journal = {CoRR},
volume = {abs/1510.05937},
year = {2015},
url = {http://arxiv.org/abs/1510.05937},
eprinttype = {arXiv},
eprint = {1510.05937},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LiWXYZ15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LiWXZ15,
author = {Lantian Li and
Dong Wang and
Chao Xing and
Thomas Fang Zheng},
title = {Max-margin Metric Learning for Speaker Recognition},
journal = {CoRR},
volume = {abs/1510.05940},
year = {2015},
url = {http://arxiv.org/abs/1510.05940},
eprinttype = {arXiv},
eprint = {1510.05940},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LiWXZ15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LuoWLP15,
author = {Tianyi Luo and
Dong Wang and
Rong Liu and
Yiqiao Pan},
title = {Stochastic Top-k ListNet},
journal = {CoRR},
volume = {abs/1511.00271},
year = {2015},
url = {http://arxiv.org/abs/1511.00271},
eprinttype = {arXiv},
eprint = {1511.00271},
timestamp = {Fri, 04 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/LuoWLP15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/WangZ15d,
author = {Dong Wang and
Thomas Fang Zheng},
title = {Transfer Learning for Speech and Language Processing},
journal = {CoRR},
volume = {abs/1511.06066},
year = {2015},
url = {http://arxiv.org/abs/1511.06066},
eprinttype = {arXiv},
eprint = {1511.06066},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/WangZ15d.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/csl/TejedorTWKC14,
author = {Javier Tejedor and
Doroteo T. Toledano and
Dong Wang and
Simon King and
Jos{\'{e}} Col{\'{a}}s},
title = {Feature analysis for discriminative confidence estimation in spoken
term detection},
journal = {Comput. Speech Lang.},
volume = {28},
number = {5},
pages = {1083--1114},
year = {2014},
url = {https://doi.org/10.1016/j.csl.2013.09.008},
doi = {10.1016/J.CSL.2013.09.008},
timestamp = {Mon, 29 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/csl/TejedorTWKC14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/WangWZZS14,
author = {Jun Wang and
Dong Wang and
Ziwei Zhu and
Thomas Fang Zheng and
Frank K. Soong},
title = {Discriminative scoring for speaker recognition based on I-vectors},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2014, Chiang Mai, Thailand, December
9-12, 2014},
pages = {1--5},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/APSIPA.2014.7041619},
doi = {10.1109/APSIPA.2014.7041619},
timestamp = {Wed, 06 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/WangWZZS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/XingWZL14,
author = {Chao Xing and
Dong Wang and
Xuewei Zhang and
Chao Liu},
title = {Document classification with distributions of word vectors},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2014, Chiang Mai, Thailand, December
9-12, 2014},
pages = {1--5},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/APSIPA.2014.7041633},
doi = {10.1109/APSIPA.2014.7041633},
timestamp = {Fri, 09 Feb 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/XingWZL14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/chinasip/BieWWZ14,
author = {Fanhu Bie and
Jun Wang and
Dong Wang and
Thomas Fang Zheng},
title = {Block-wise training for i-vector},
booktitle = {{IEEE} China Summit {\&} International Conference on Signal and
Information Processing, ChinaSIP 2014, Xi'an, China, July 9-13, 2014},
pages = {11--15},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ChinaSIP.2014.6889192},
doi = {10.1109/CHINASIP.2014.6889192},
timestamp = {Sun, 22 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/chinasip/BieWWZ14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/chinasip/MengLZW14,
author = {Xiangtao Meng and
Chao Liu and
Zhiyong Zhang and
Dong Wang},
title = {Noisy training for deep neural networks},
booktitle = {{IEEE} China Summit {\&} International Conference on Signal and
Information Processing, ChinaSIP 2014, Xi'an, China, July 9-13, 2014},
pages = {16--20},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ChinaSIP.2014.6889193},
doi = {10.1109/CHINASIP.2014.6889193},
timestamp = {Fri, 09 Feb 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/chinasip/MengLZW14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iberspeech/TejedorTW14,
author = {Javier Tejedor and
Doroteo T. Toledano and
Dong Wang},
editor = {Juan Luis Navarro Mesa and
Alfonso Ortega and
Ant{\'{o}}nio J. S. Teixeira and
Eduardo Hern{\'{a}}ndez{-}P{\'{e}}rez and
Pedro J. Quintana{-}Morales and
Antonio G. Ravelo{-}Garc{\'{\i}}a and
Iv{\'{a}}n Guerra Moreno and
Doroteo T. Toledano},
title = {ATVS-CSLT-HCTLab System for {NIST} 2013 Open Keyword Search Evaluation},
booktitle = {Advances in Speech and Language Technologies for Iberian Languages
- Second International Conference, IberSPEECH 2014, Las Palmas de
Gran Canaria, Spain, November 19-21, 2014. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {8854},
pages = {249--258},
publisher = {Springer},
year = {2014},
url = {https://doi.org/10.1007/978-3-319-13623-3\_26},
doi = {10.1007/978-3-319-13623-3\_26},
timestamp = {Thu, 23 Jun 2022 19:58:00 +0200},
biburl = {https://dblp.org/rec/conf/iberspeech/TejedorTW14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiuZW14,
author = {Chao Liu and
Zhiyong Zhang and
Dong Wang},
editor = {Haizhou Li and
Helen M. Meng and
Bin Ma and
Engsiong Chng and
Lei Xie},
title = {Pruning deep neural networks by optimal brain damage},
booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech
Communication Association, Singapore, September 14-18, 2014},
pages = {1092--1095},
publisher = {{ISCA}},
year = {2014},
url = {https://doi.org/10.21437/Interspeech.2014-281},
doi = {10.21437/INTERSPEECH.2014-281},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiuZW14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iscslp/LiuWX14,
author = {Rong Liu and
Dong Wang and
Chao Xing},
editor = {Minghui Dong and
Jianhua Tao and
Haizhou Li and
Thomas Fang Zheng and
Yanfeng Lu},
title = {Document classification based on c},
booktitle = {The 9th International Symposium on Chinese Spoken Language Processing,
Singapore, September 12-14, 2014},
pages = {413},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ISCSLP.2014.6936669},
doi = {10.1109/ISCSLP.2014.6936669},
timestamp = {Mon, 18 Mar 2024 17:29:23 +0100},
biburl = {https://dblp.org/rec/conf/iscslp/LiuWX14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iscslp/WangLWZ14,
author = {Jun Wang and
Lantian Li and
Dong Wang and
Thomas Fang Zheng},
editor = {Minghui Dong and
Jianhua Tao and
Haizhou Li and
Thomas Fang Zheng and
Yanfeng Lu},
title = {Research on generalization property of time-varying Fbank-weighted
{MFCC} for i-vector based speaker verification},
booktitle = {The 9th International Symposium on Chinese Spoken Language Processing,
Singapore, September 12-14, 2014},
pages = {423},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ISCSLP.2014.6936667},
doi = {10.1109/ISCSLP.2014.6936667},
timestamp = {Sun, 22 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iscslp/WangLWZ14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iscslp/BieWZ14,
author = {Fanhu Bie and
Dong Wang and
Thomas Fang Zheng},
editor = {Minghui Dong and
Jianhua Tao and
Haizhou Li and
Thomas Fang Zheng and
Yanfeng Lu},
title = {Research on truncated speech in speaker verification},
booktitle = {The 9th International Symposium on Chinese Spoken Language Processing,
Singapore, September 12-14, 2014},
pages = {425},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ISCSLP.2014.6936671},
doi = {10.1109/ISCSLP.2014.6936671},
timestamp = {Tue, 06 Feb 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iscslp/BieWZ14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mta/TejedorEWV13,
author = {Javier Tejedor and
Alejandro Echeverr{\'{\i}}a and
Dong Wang and
Ravichander Vipperla},
title = {Evolutionary discriminative confidence estimation for spoken term
detection},
journal = {Multim. Tools Appl.},
volume = {62},
number = {1},
pages = {5--34},
year = {2013},
url = {https://doi.org/10.1007/s11042-011-0913-z},
doi = {10.1007/S11042-011-0913-Z},
timestamp = {Mon, 03 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/mta/TejedorEWV13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tsp/WangVEZ13,
author = {Dong Wang and
Ravichander Vipperla and
Nicholas W. D. Evans and
Thomas Fang Zheng},
title = {Online Non-Negative Convolutive Pattern Learning for Speech Signals},
journal = {{IEEE} Trans. Signal Process.},
volume = {61},
number = {1},
pages = {44--56},
year = {2013},
url = {https://doi.org/10.1109/TSP.2012.2222381},
doi = {10.1109/TSP.2012.2222381},
timestamp = {Tue, 10 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tsp/WangVEZ13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/BieWZTC13,
author = {Fanhu Bie and
Dong Wang and
Thomas Fang Zheng and
Javier Tejedor and
Ruxin Chen},
title = {Emotional adaptive training for speaker verification},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2013, Kaohsiung, Taiwan, October 29
- November 1, 2013},
pages = {1--4},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/APSIPA.2013.6694123},
doi = {10.1109/APSIPA.2013.6694123},
timestamp = {Mon, 03 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/BieWZTC13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/chinasip/BieWZC13,
author = {Fanhu Bie and
Dong Wang and
Thomas Fang Zheng and
Ruxin Chen},
title = {Emotional speaker verification with linear adaptation},
booktitle = {2013 {IEEE} China Summit and International Conference on Signal and
Information Processing, ChinaSIP 2013, Beijing, China, July 6-10,
2013},
pages = {91--94},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ChinaSIP.2013.6625304},
doi = {10.1109/CHINASIP.2013.6625304},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/chinasip/BieWZC13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/chinasip/WangWWZ13,
author = {Jun Wang and
Dong Wang and
Xiaojun Wu and
Thomas Fang Zheng},
title = {Sequential {UBM} adaptation for speaker verification},
booktitle = {2013 {IEEE} China Summit and International Conference on Signal and
Information Processing, ChinaSIP 2013, Beijing, China, July 6-10,
2013},
pages = {356--359},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ChinaSIP.2013.6625360},
doi = {10.1109/CHINASIP.2013.6625360},
timestamp = {Sun, 22 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/chinasip/WangWWZ13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/QiWT13,
author = {Jun Qi and
Dong Wang and
Javier Tejedor},
editor = {Fr{\'{e}}d{\'{e}}ric Bimbot and
Christophe Cerisara and
C{\'{e}}cile Fougeron and
Guillaume Gravier and
Lori Lamel and
Fran{\c{c}}ois Pellegrino and
Pascal Perrier},
title = {Subspace models for bottleneck features},
booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech
Communication Association, Lyon, France, August 25-29, 2013},
pages = {1746--1750},
publisher = {{ISCA}},
year = {2013},
url = {https://doi.org/10.21437/Interspeech.2013-434},
doi = {10.21437/INTERSPEECH.2013-434},
timestamp = {Sun, 06 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/QiWT13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/QiWXT13,
author = {Jun Qi and
Dong Wang and
Ji Xu and
Javier Tejedor},
editor = {Fr{\'{e}}d{\'{e}}ric Bimbot and
Christophe Cerisara and
C{\'{e}}cile Fougeron and
Guillaume Gravier and
Lori Lamel and
Fran{\c{c}}ois Pellegrino and
Pascal Perrier},
title = {Bottleneck features based on gammatone frequency cepstral coefficients},
booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech
Communication Association, Lyon, France, August 25-29, 2013},
pages = {1751--1755},
publisher = {{ISCA}},
year = {2013},
url = {https://doi.org/10.21437/Interspeech.2013-435},
doi = {10.21437/INTERSPEECH.2013-435},
timestamp = {Sun, 06 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/QiWXT13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/WangWWZT13,
author = {Jun Wang and
Dong Wang and
Xiaojun Wu and
Thomas Fang Zheng and
Javier Tejedor},
editor = {Fr{\'{e}}d{\'{e}}ric Bimbot and
Christophe Cerisara and
C{\'{e}}cile Fougeron and
Guillaume Gravier and
Lori Lamel and
Fran{\c{c}}ois Pellegrino and
Pascal Perrier},
title = {Sequential model adaptation for speaker verification},
booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech
Communication Association, Lyon, France, August 25-29, 2013},
pages = {2460--2464},
publisher = {{ISCA}},
year = {2013},
url = {https://doi.org/10.21437/Interspeech.2013-410},
doi = {10.21437/INTERSPEECH.2013-410},
timestamp = {Sun, 06 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/WangWWZT13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iscas/QiWJL13,
author = {Jun Qi and
Dong Wang and
Yi Jiang and
Runsheng Liu},
title = {Auditory features based on Gammatone filters for robust speech recognition},
booktitle = {2013 {IEEE} International Symposium on Circuits and Systems (ISCAS2013),
Beijing, China, May 19-23, 2013},
pages = {305--308},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ISCAS.2013.6571843},
doi = {10.1109/ISCAS.2013.6571843},
timestamp = {Tue, 20 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iscas/QiWJL13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jcst/WangTKF12,
author = {Dong Wang and
Javier Tejedor and
Simon King and
Joe Frankel},
title = {Term-Dependent Confidence Normalisation for Out-of-Vocabulary Spoken
Term Detection},
journal = {J. Comput. Sci. Technol.},
volume = {27},
number = {2},
pages = {358--375},
year = {2012},
url = {https://doi.org/10.1007/s11390-012-1228-x},
doi = {10.1007/S11390-012-1228-X},
timestamp = {Mon, 29 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jcst/WangTKF12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/EvansBWFT12,
author = {Nicholas W. D. Evans and
Simon Bozonnet and
Dong Wang and
Corinne Fredouille and
Rapha{\"{e}}l Troncy},
title = {A Comparative Study of Bottom-Up and Top-Down Approaches to Speaker
Diarization},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {20},
number = {2},
pages = {382--392},
year = {2012},
url = {https://doi.org/10.1109/TASL.2011.2159710},
doi = {10.1109/TASL.2011.2159710},
timestamp = {Sun, 17 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/EvansBWFT12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tois/WangKFVET12,
author = {Dong Wang and
Simon King and
Joe Frankel and
Ravichander Vipperla and
Nicholas W. D. Evans and
Rapha{\"{e}}l Troncy},
title = {Direct posterior confidence for out-of-vocabulary spoken term detection},
journal = {{ACM} Trans. Inf. Syst.},
volume = {30},
number = {3},
pages = {16:1--16:34},
year = {2012},
url = {https://doi.org/10.1145/2328967.2328969},
doi = {10.1145/2328967.2328969},
timestamp = {Mon, 29 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tois/WangKFVET12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/VipperlaGBWESR12,
author = {Ravichander Vipperla and
J{\"{u}}rgen T. Geiger and
Simon Bozonnet and
Dong Wang and
Nicholas W. D. Evans and
Bj{\"{o}}rn W. Schuller and
Gerhard Rigoll},
title = {Speech overlap detection and attribution using convolutive non-negative
sparse coding},
booktitle = {2012 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2012, Kyoto, Japan, March 25-30, 2012},
pages = {4181--4184},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/ICASSP.2012.6288840},
doi = {10.1109/ICASSP.2012.6288840},
timestamp = {Sat, 05 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/VipperlaGBWESR12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiuWT12,
author = {Chao Liu and
Dong Wang and
Javier Tejedor},
title = {N-gram {FST} Indexing for Spoken Term Detection},
booktitle = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
Communication Association, Portland, Oregon, USA, September 9-13,
2012},
pages = {2093--2096},
publisher = {{ISCA}},
year = {2012},
url = {https://doi.org/10.21437/Interspeech.2012-558},
doi = {10.21437/INTERSPEECH.2012-558},
timestamp = {Sun, 06 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiuWT12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/WangT12,
author = {Dong Wang and
Javier Tejedor},
title = {Heterogeneous Convolutive Non-Negative Sparse Coding},
booktitle = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
Communication Association, Portland, Oregon, USA, September 9-13,
2012},
pages = {2150--2153},
publisher = {{ISCA}},
year = {2012},
url = {https://doi.org/10.21437/Interspeech.2012-574},
doi = {10.21437/INTERSPEECH.2012-574},
timestamp = {Sun, 06 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/WangT12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/spl/WangK11,
author = {Dong Wang and
Simon King},
title = {Letter-to-Sound Pronunciation Prediction Using Conditional Random
Fields},
journal = {{IEEE} Signal Process. Lett.},
volume = {18},
number = {2},
pages = {122--125},
year = {2011},
url = {https://doi.org/10.1109/LSP.2010.2098440},
doi = {10.1109/LSP.2010.2098440},
timestamp = {Mon, 29 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/spl/WangK11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/WangKF11,
author = {Dong Wang and
Simon King and
Joe Frankel},
title = {Stochastic Pronunciation Modeling for Out-of-Vocabulary Spoken Term
Detection},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {19},
number = {4},
pages = {688--698},
year = {2011},
url = {https://doi.org/10.1109/TASL.2010.2058800},
doi = {10.1109/TASL.2010.2058800},
timestamp = {Mon, 29 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/WangKF11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cbmi/TejedorEW11,
author = {Javier Tejedor and
Alejandro Echeverr{\'{\i}}a and
Dong Wang},
editor = {Jos{\'{e}} M. Mart{\'{\i}}nez},
title = {An evolutionary confidence measurement for spoken term detection},
booktitle = {9th International Workshop on Content-Based Multimedia Indexing, {CBMI}
2011, Madrid, Spain, June 13-15, 2011},
pages = {151--156},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/CBMI.2011.5972537},
doi = {10.1109/CBMI.2011.5972537},
timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cbmi/TejedorEW11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/BozonnetWET11,
author = {Simon Bozonnet and
Dong Wang and
Nicholas W. D. Evans and
Rapha{\"{e}}l Troncy},
title = {Linguistic influences on bottom-up and top-down clustering for speaker
diarization},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2011, May 22-27, 2011, Prague Congress
Center, Prague, Czech Republic},
pages = {4424--4427},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ICASSP.2011.5947335},
doi = {10.1109/ICASSP.2011.5947335},
timestamp = {Mon, 16 Sep 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/BozonnetWET11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/WangETK11,
author = {Dong Wang and
Nicholas W. D. Evans and
Rapha{\"{e}}l Troncy and
Simon King},
title = {Handling overlaps in spoken term detection},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2011, May 22-27, 2011, Prague Congress
Center, Prague, Czech Republic},
pages = {5656--5659},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ICASSP.2011.5947643},
doi = {10.1109/ICASSP.2011.5947643},
timestamp = {Mon, 29 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/WangETK11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/WangVE11,
author = {Dong Wang and
Ravichander Vipperla and
Nicholas W. D. Evans},
title = {Online Pattern Learning for Non-Negative Convolutive Sparse Coding},
booktitle = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech
Communication Association, Florence, Italy, August 27-31, 2011},
pages = {65--68},
publisher = {{ISCA}},
year = {2011},
url = {https://doi.org/10.21437/Interspeech.2011-17},
doi = {10.21437/INTERSPEECH.2011-17},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/WangVE11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/WangVE11a,
author = {Dong Wang and
Ravichander Vipperla and
Nicholas W. D. Evans},
title = {Parallel and Hierarchical Decision Making for Sparse Coding in Speech
Recognition},
booktitle = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech
Communication Association, Florence, Italy, August 27-31, 2011},
pages = {2557--2560},
publisher = {{ISCA}},
year = {2011},
url = {https://doi.org/10.21437/Interspeech.2011-654},
doi = {10.21437/INTERSPEECH.2011-654},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/WangVE11a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/WangKFB10,
author = {Dong Wang and
Simon King and
Joe Frankel and
Peter Bell},
title = {Stochastic pronunciation modelling and soft match for out-of-vocabulary
spoken term detection},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2010, 14-19 March 2010, Sheraton Dallas
Hotel, Dallas, Texas, {USA}},
pages = {5294--5297},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5494968},
doi = {10.1109/ICASSP.2010.5494968},
timestamp = {Mon, 29 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/WangKFB10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TejedorTBKWC10,
author = {Javier Tejedor and
Doroteo T. Toledano and
Miguel Bautista and
Simon King and
Dong Wang and
Jos{\'{e}} Col{\'{a}}s},
editor = {Takao Kobayashi and
Keikichi Hirose and
Satoshi Nakamura},
title = {Augmented set of features for confidence estimation in spoken term
detection},
booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech
Communication Association, Makuhari, Chiba, Japan, September 26-30,
2010},
pages = {701--704},
publisher = {{ISCA}},
year = {2010},
url = {https://doi.org/10.21437/Interspeech.2010-264},
doi = {10.21437/INTERSPEECH.2010-264},
timestamp = {Sat, 03 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/TejedorTBKWC10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/WangKET10,
author = {Dong Wang and
Simon King and
Nicholas W. D. Evans and
Rapha{\"{e}}l Troncy},
editor = {Takao Kobayashi and
Keikichi Hirose and
Satoshi Nakamura},
title = {CRF-based stochastic pronunciation modeling for out-of-vocabulary
spoken term detection},
booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech
Communication Association, Makuhari, Chiba, Japan, September 26-30,
2010},
pages = {1668--1671},
publisher = {{ISCA}},
year = {2010},
url = {https://doi.org/10.21437/Interspeech.2010-481},
doi = {10.21437/INTERSPEECH.2010-481},
timestamp = {Sat, 03 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/WangKET10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/BozonnetEFWT10,
author = {Simon Bozonnet and
Nicholas W. D. Evans and
Corinne Fredouille and
Dong Wang and
Rapha{\"{e}}l Troncy},
editor = {Takao Kobayashi and
Keikichi Hirose and
Satoshi Nakamura},
title = {An integrated top-down/bottom-up approach to speaker diarization},
booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech
Communication Association, Makuhari, Chiba, Japan, September 26-30,
2010},
pages = {2646--2649},
publisher = {{ISCA}},
year = {2010},
url = {https://doi.org/10.21437/Interspeech.2010-702},
doi = {10.21437/INTERSPEECH.2010-702},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/BozonnetEFWT10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mm/WangKD10,
author = {Dong Wang and
Simon King and
Nicholas W. D. Evans},
editor = {Martha A. Larson and
Roeland Ordelman and
Florian Metze and
Franciska de Jong and
Wessel Kraaij},
title = {Evans, Joe Frankel, Rapha{\"{e}}l Troncy: Direct posterior confidence
for out-of-vocabulary spoken term detection},
booktitle = {Proceedings of the 2010 International Workshop on Searching Spontaneous
Conversational Speech, {SSCS} '10, Firenze, Italy, October 29, 2010},
pages = {21--26},
publisher = {{ACM}},
year = {2010},
url = {https://doi.org/10.1145/1878101.1878107},
doi = {10.1145/1878101.1878107},
timestamp = {Mon, 29 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/mm/WangKD10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/paams/EcheverriaTW10,
author = {Alejandro Echeverr{\'{\i}}a and
Javier Tejedor and
Dong Wang},
editor = {Yves Demazeau and
Frank Dignum and
Juan M. Corchado and
Javier Bajo and
Rafael Corchuelo and
Emilio Corchado and
Florentino Fern{\'{a}}ndez Riverola and
Vicente Juli{\'{a}}n and
Pawel Pawlewski and
Andrew T. Campbell},
title = {An Evolutionary Confidence Measure for Spotting Words in Speech Recognition},
booktitle = {Trends in Practical Applications of Agents and Multiagent Systems
- 8th International Conference on Practical Applications of Agents
and Multiagent Systems, {PAAMS} 2010 Special Sessions and Workshops,
Salamanca, Spain, 26-28 April 2010},
series = {Advances in Intelligent and Soft Computing},
volume = {71},
pages = {419--427},
publisher = {Springer},
year = {2010},
url = {https://doi.org/10.1007/978-3-642-12433-4\_50},
doi = {10.1007/978-3-642-12433-4\_50},
timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/paams/EcheverriaTW10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/WangTFKC09,
author = {Dong Wang and
Javier Tejedor and
Joe Frankel and
Simon King and
Jos{\'{e}} Col{\'{a}}s},
title = {Posterior-based confidence measures for spoken term detection},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan},
pages = {4889--4892},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ICASSP.2009.4960727},
doi = {10.1109/ICASSP.2009.4960727},
timestamp = {Mon, 29 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/WangTFKC09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TejedorWKFC09,
author = {Javier Tejedor and
Dong Wang and
Simon King and
Joe Frankel and
Jos{\'{e}} Col{\'{a}}s},
title = {A posterior probability-based system hybridisation and combination
for spoken term detection},
booktitle = {{INTERSPEECH} 2009, 10th Annual Conference of the International Speech
Communication Association, Brighton, United Kingdom, September 6-10,
2009},
pages = {2131--2134},
publisher = {{ISCA}},
year = {2009},
url = {https://doi.org/10.21437/Interspeech.2009-609},
doi = {10.21437/INTERSPEECH.2009-609},
timestamp = {Fri, 02 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/TejedorWKFC09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/WangKF09,
author = {Dong Wang and
Simon King and
Joe Frankel},
title = {Stochastic pronunciation modelling for spoken term detection},
booktitle = {{INTERSPEECH} 2009, 10th Annual Conference of the International Speech
Communication Association, Brighton, United Kingdom, September 6-10,
2009},
pages = {2135--2138},
publisher = {{ISCA}},
year = {2009},
url = {https://doi.org/10.21437/Interspeech.2009-610},
doi = {10.21437/INTERSPEECH.2009-610},
timestamp = {Fri, 02 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/WangKF09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/WangKFB09,
author = {Dong Wang and
Simon King and
Joe Frankel and
Peter Bell},
title = {Term-dependent confidence for out-of-vocabulary term detection},
booktitle = {{INTERSPEECH} 2009, 10th Annual Conference of the International Speech
Communication Association, Brighton, United Kingdom, September 6-10,
2009},
pages = {2139--2142},
publisher = {{ISCA}},
year = {2009},
url = {https://doi.org/10.21437/Interspeech.2009-611},
doi = {10.21437/INTERSPEECH.2009-611},
timestamp = {Fri, 02 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/WangKFB09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/TejedorWFKC08,
author = {Javier Tejedor and
Dong Wang and
Joe Frankel and
Simon King and
Jos{\'{e}} Col{\'{a}}s},
title = {A comparison of grapheme and phoneme-based units for Spanish spoken
term detection},
journal = {Speech Commun.},
volume = {50},
number = {11-12},
pages = {980--991},
year = {2008},
url = {https://doi.org/10.1016/j.specom.2008.03.005},
doi = {10.1016/J.SPECOM.2008.03.005},
timestamp = {Mon, 29 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/speech/TejedorWFKC08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/WangFTK08,
author = {Dong Wang and
Joe Frankel and
Javier Tejedor and
Simon King},
title = {A comparison of phone and grapheme-based spoken term detection},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2008, March 30 - April 4, 2008, Caesars
Palace, Las Vegas, Nevada, {USA}},
pages = {4969--4972},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ICASSP.2008.4518773},
doi = {10.1109/ICASSP.2008.4518773},
timestamp = {Mon, 29 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/WangFTK08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/WangHFK08,
author = {Dong Wang and
Ivan Himawan and
Joe Frankel and
Simon King},
title = {A posterior approach for microphone array based speech recognition},
booktitle = {{INTERSPEECH} 2008, 9th Annual Conference of the International Speech
Communication Association, Brisbane, Australia, September 22-26, 2008},
pages = {996--999},
publisher = {{ISCA}},
year = {2008},
url = {https://doi.org/10.21437/Interspeech.2008-290},
doi = {10.21437/INTERSPEECH.2008-290},
timestamp = {Fri, 02 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/WangHFK08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/FrankelWK08,
author = {Joe Frankel and
Dong Wang and
Simon King},
title = {Growing bottleneck features for tandem {ASR}},
booktitle = {{INTERSPEECH} 2008, 9th Annual Conference of the International Speech
Communication Association, Brisbane, Australia, September 22-26, 2008},
pages = {1549},
publisher = {{ISCA}},
year = {2008},
url = {https://www.isca-speech.org/archive/interspeech\_2008/frankel08\_interspeech.html},
timestamp = {Fri, 02 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/FrankelWK08.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 06:22 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:
