“ASR-nsfc-publication”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
 
(2位用户的32个中间修订版本未显示)
第1行: 第1行:
==Journal papers==
+
==Journal papers (SCI)==
 +
# Lantian Li, Ruiqi Liu, Jiawen Kang, Yue Fa, Hao Cui, Yunqi Cai, Ravichander Vipperla, Thomas Fang Zheng and Dong Wang. "CN-Celeb: multi-genre speaker recognition", Speech Communication, 2022. [https://arxiv.org/pdf/2012.12468 pdf]
 +
# Lantian Li, Dong Wang etc., A Principle Solution for Enroll-Test Mismatch, IEEE Transaction on Audio, Speech and Language Processing, 2021 [https://arxiv.org/pdf/2012.12471.pdf pdf]
 +
# Yunqi Cai, Lantian Li, Andrew Abel, Xiaoyan Zhu, Dong Wang, "Deep Normalization for Speaker Vectors", IEEE Transactions on Audio, Speech and Language Processing, 2020. [https://arxiv.org/pdf/2004.04095.pdf pdf]
 +
# Dong Wang, "A Simulation Study on Optimal Scores for Speaker Recognition", EURASIP Journal on Audio, Speech, and Music Processing, 2020. [http://wangd.cslt.org/public/pdf/nl-eurosip.pdf pdf]
 +
# Gulnur Arkin, Askar Hamdulla and Mijit Ablimit , Analysis of phonemes and tones confusion rules obtained by ASR,Wireless Networks,2020.[https://link.springer.com/article/10.1007%2Fs11276-019-02220-2 link]
 +
# Zhiyuan Tang, Lantian Li, Dong Wang,  Ravichander Vipperla, "Collaborative Joint Training With Multitask Recurrent Model for Speech and Speaker Recognition", IEEE Transactions on Audio, Speech and Language Processing 2018, vol 25, no.3. [http://ieeexplore.ieee.org/document/7782371 online]
 +
# Zhiyuan Tang,Dong Wang,Yixiang Chen,Lantian Li,Andrew Abel, "Phonetic Temporal Neural Model for Language Identification", IEEE Transactions on Audio, Speech and Language Processing 2017. [http://ieeexplore.ieee.org/document/8070977 online]
  
# Zhiyuan Tang, Lantian Li, Dong Wang,  Ravichander Vipperla, "Collaborative Joint Training With Multitask Recurrent Model for Speech and Speaker Recognition", IEEE TASLP 2017, vol 25, no.3. [http://ieeexplore.ieee.org/document/7782371 online]
+
==Journal papers (EI)==
# Zhiyuan Tang,Dong Wang,Yixiang Chen,Lantian Li,Andrew Abel, "Phonetic Temporal Neural Model for Language Identification", IEEE TASLP 2017. [http://ieeexplore.ieee.org/document/8070977 online]  
+
# Siamese Attention-based LSTM for Speech Emotion Recognition,IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, v E103A, n 7, p 937-941, July 1, 2020 [https://search.ieice.org/bin/summary.php?id=e103-a_7_937 link]
==Conference papers==
+
# Uyghur short-text classification based on reliable sub-word morphology, International Journal of Reasoning-based Intelligent Systems,v 11, n 3, p 250-255, 2019 [https://www.inderscienceonline.com/doi/abs/10.1504/IJRIS.2019.102606 link]
 +
# A Robust Morpheme Sequence and Convolutional Neural Network-Based Uyghur and Kazakh Short Text Classification, Information (Switzerland), v 10, n 12, December 1, 2019 [https://www.mdpi.com/2078-2489/10/12/387/pdf pdf]
  
# Yang Feng, Shiyue Zhang, Andy Zhang, Dong Wang and Andrew Abel, Memory-augmented Neural Machine Translation, EMNLP 2017 [http://wangd.cslt.org/public/pdf/memory-augmented-nmt.pdf] .
+
 
# Lantian Li, Yixiang Chen, Dong Wang, Thomas Fang Zheng, A Study on Replay Attack and Anti-Spoofing for Automatic Speaker Verification, Interspeech 2017 [https://arxiv.org/pdf/1705.03670.pdf].
+
==Conference papers (EI)==
# Lantian Li, Yixiang Chen, Ying Shi, Zhiyuan Tang, Dong Wang, "Deep Speaker Feature Learning for Text-independent Speaker Verification", Interspeech 2017[https://arxiv.org/pdf/1705.03670.pdf].
+
# Tiankai Zhi, Ying Shi, Wenqiang Du, Guanyu Li and Dong Wang, "A Free Mongolian Speech Database and Accompanied Baselines", O-COCOSDA 2021.[]
# Jiyuan Zhang, Yang Feng, Dong Wang, Yang Wang, Andrw Abel, Shiyue Zhang, Andi Zhangi, "Flexible and Creative Chinese Poetry Generation Using Neural Memory", ACL 2017 [https://arxiv.org/abs/1705.03773]
+
# Jiao Han, Yunqi Cai, Lantian Li, Guanyu Li, Dong Wang, "An MAP Estimation for Between-Class Variance", APSIPA 2021. []
# Zhiyuan Tang, Ying Shi, Dong Wang, Yang Feng, and Shiyue Zhang, "Memory Visualization for Gated Recurrent Neural Networks in Speech Recognition", ICASSP 2017.[https://arxiv.org/abs/1609.08789]
+
# Di Wang, Lantian Li, Hongzhi Yu, Dong Wang,A STUDY ON DECOUPLED PROBABILISTIC LINEAR DISCRIMINANT ANALYSIS, APSIPA 2021.
 +
# Haoran Sun, Lantian Li, Thomas Fang Zheng, Dong Wang, HOW SPEECH IS RECOGNIZED TO BE EMOTIONAL - A STUDY BASED ON INFORMATION DECOMPOSITION, APSIPA 2021.
 +
# Lantian Li, Yang Zhang, Jiawen Kang, Thomas Fang Zheng, Dong Wang, "SQUEEZING VALUE OF CROSS-DOMAIN LABELS: A DECOUPLED SCORING APPROACH FOR SPEAKER VERIFICATION", ICASSP 2021. [pdf]
 +
# Ying Shi, Haolin Chen, Zhiyuan Tang, Lantian Li, Dong Wang, Jiqing Han, Can We Trust Deep Speech Prior?, SLT 2021[https://arxiv.org/abs/2011.02110 pdf pdf]
 +
# Zheng Li, Miao Zhao, Qingyang Hong, Lin Li, Zhiyuan Tang, Dong Wang, Liming Song, Cheng Yang, "AP20-OLR Challenge: Three Tasks and TheirBaselines", APSIPA 2020. [https://arxiv.org/pdf/2006.03473.pdf pdf]
 +
# Jiawen Kang,Ruiqi Liu,Lantian Li,Yunqi Cai,Dong Wang,Thomas Fang Zheng, "Domain-Invariant Speaker Vector Projection by Model-Agnostic Meta-Learning", Interspeech 2020. [https://arxiv.org/pdf/2005.11900.pdf pdf]
 +
# Sitong Cheng,Zhixin Liu,Lantian Li,Zhiyuan Tang,Dong Wang,Thomas Fang Zheng, "ASR-Free Pronunciation Assessment", Interspeech 2020. [https://arxiv.org/pdf/2005.11902.pdf pdf]
 +
# Lantian Li,Dong Wang,Thomas Fang Zheng, "Neural Discriminant Analysis for Deep Speaker Embedding", Interspeech 2020. [https://arxiv.org/pdf/2005.11905.pdf pdf]
 +
# Yongmin Li, Guanyu Lia, Pengqi Lia, Sixuan Lia, Xinyu Yuan, ”A Survey of Multimodal Fusion for Identity Verification”, International Symposium on Electronic Information Technology and Communication Engineering(ISEITCE), 2020 [https://iopscience.iop.org/article/10.1088/1742-6596/1607/1/012126/pdf pdf]
 +
# Yue Fan, Jiawen Kang, Lantian Li, Kaicheng Li, Haolin Chen, Sitong Cheng, Pengyuan Zhang, Ziya Zhou, Yunqi Cai, Dong Wang, "CN-CELEB: A Challenging Chinese Speaker Recognition Dataset", ICASSP 2020. [https://arxiv.org/pdf/1911.01799.pdf pdf]
 +
# Wupeng Wang, Chao Xing, Dong Wang, Xiao Chen, Fengyu Sun, "A ROBUST AUDIO-VISUAL SPEECH ENHANCEMENT MODEL", ICASSP 2020, [http://166.111.134.19:7777/wangd/public/pdf/visual.pdf pdf]
 +
# Yang Zhang and Lantian Li and Dong Wang, "VAE-based regularization for deep speaker embedding", Interspeech 2019 [https://arxiv.org/abs/1904.03617 pdf]
 +
# Lantian Li,Zhiyuan Tang,Ying Shi,Dong Wang, "Gaussian-Constrained Training for Speaker Verification", ICASSP 2019[https://arxiv.org/abs/1811.03258 pdf]
 +
# Sardar Parhat, Gao Ting, Mijit Ablimit, Askar Hamdulla, A morpheme sequence and convolutional neural network based Kazakh text classification,2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019, p 1903-1906, November 2019 [http://www.apsipa.org/proceedings/2019/pdfs/319.pdf pdf]
 +
# Arkin G, Alijan G, Hamdulla A, A Comparative Analysis of Acoustic Characteristics between Kazak Uyghur Mandarin Learners and Standard Mandarin Speakers,Proceedings of the 2019 International Conference on Asian Language Processing, IALP 2019, p 474-479, November 2019 [https://ieeexplore.ieee.org/abstract/document/9037703/ link]
 +
# Statistical Analysis of Syllable Duration of Uyghur Language,Proceedings of the 2019 International Conference on Asian Language Processing, IALP 2019, p 468-473, November 2019 [https://ieeexplore.ieee.org/abstract/document/9037656]
 +
# Lantian Li,Zhiyuan Tang,Ying Shi,Dong Wang, "Phonetic-Attention Scoring for Deep Speaker Features in Speaker Verification", APSIPA 2019 [https://arxiv.org/pdf/1811.03255.pdf pdf]
 +
# Lantian Li*,Xueyi Wang*,Dong Wang, "VAE-based Domain Adaptation for Speaker Verification", APSIPA 2019.  [https://arxiv.org/pdf/1908.10092.pdf pdf]
 +
# Jiayao Wu, Zhiyuan Tang and Dong Wang, "Structure Growth for Small-Footprint Speech Recognition", APSIPA 2019. [http://www.apsipa.org/proceedings/2019/pdfs/449.pdf pdf]
 +
# Zhiyuan Tang, Dong Wang, Liming Song, "AP19-OLR Challenge: Three Tasks and Their Baselines", APSIPA 2019. [https://arxiv.org/pdf/1907.07626.pdf pdf]
 +
# Yunqi Cai, Dong Wang, "Question Mark Prediction By Bert", APSIPA 2019 [http://www.apsipa.org/proceedings/2019/pdfs/180.pdf pdf]
 +
# Guanyu Li, Lisai Luo, Chunwei Gong, Shiliang Lv, “End-to-end Tibetan Speech Synthesis Based on Phones and Semi-syllables”, Proceedings of APSIPA Annual Summit and Conference(APSIPA) 2019 [http://www.apsipa.org/proceedings/2019/pdfs/308.pdf pdf]
 +
# Duo Ma, Guanyu Li, Haihua Xu, Eng Siong Chng, “Improving code-switching speech recognition with data augmentation and system combination”, Proceedings of APSIPA Annual Summit and Conference(APSIPA) 2019 [http://www.apsipa.org/proceedings/2019/pdfs/339.pdf]
 +
# Jiyuan Zhang,Dong Wang, "Chinese Poetry Generation with Flexible Styles", ISCSLP 2018[https://arxiv.org/abs/1807.06500 pdf].
 +
# Jiyuan Zhang,Zheling Zhang,Shiyue Zhang, Dong Wang,"VV-COUPLET: AN OPEN SOURCE CHINESE COUPLET GENERATION SYSTEM", APSIPA 2018. [http://www.apsipa.org/proceedings/2018/pdfs/0001756.pdf pdf]
 +
# Zhiyuan Tang,Dong Wang,Qing Chen, "AP18-OLR CHALLENGE: THREE TASKS AND THEIR BASELINES",APSIPA 2018.[https://arxiv.org/abs/1806.00616 pdf]
 +
# Ying Shi,Zhiyuan Tang, Lantian Li,Zheling Zhang,Dong Wang, "MAP AND RELABEL: TOWARDS ALMOST-ZERO RESOURCE SPEECH RECOGNITION",APSIPA 2018.[http://166.111.134.19:8081/wangd/public/pdf/low_resource.pdf pdf]
 +
# Miao Zhang, Xiaofei Kang, Yanqing Wang, Lantian Li, Zhiyuan Tang, Haisheng Dai, Dong Wang*, HUMAN AND MACHINE SPEAKER RECOGNITION BASED ON SHORT TRIVIAL EVENT, ICASSP 2018 [https://arxiv.org/pdf/1711.05443 arXiv]
 +
# Jinghao Yan, Hongzhi Yu, Guanyu Li,"Tibetan acoustic model research based on TDNN", APSIPA ASC 2018 [http://www.apsipa.org/proceedings/2018/pdfs/0000601.pdf pdf]
 +
# Yultuz Rapkat; Gulnur Arkin; Mijit Ablimit; Askar Hamdulla, Acoustic Features of Mandarin Diphthongs by Uyghur Learners at Primary Level,2018 Oriental COCOSDA - International Conference on Speech Database and Assessments, ICSDA 2018 - Proceedings, p 60-66, July 2, 2018, [https://ieeexplore.ieee.org/abstract/document/8693014 link]
 +
# Mijit Ablimit*, Sardar Parhat*, Askar Hamdulla*, Thomas Fang Zheng, Multilingual Stemming and Term extraction for Uyghur, Kazak and Kirghiz,2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings, p 587-590, July 2, 2018 [http://cslt.riit.tsinghua.edu.cn/~fzheng/PAPERS/2018/1811E_APSIPA_Multilingual-Stemmning-n-Term-Extraction_Mijit.pdf pdf]
 +
# Lisai Luo, Guanyu Li1, Chunwei Gong, Hailan Ding, “End-to-end Speech Synthesis for Tibetan Lhasa Dialect”, International Symposium on Power Electronics and Control Engineering (ISPECE), 2018 [https://iopscience.iop.org/article/10.1088/1742-6596/1187/5/052061/pdf pdf]
 +
# Ning Yang, Guanyu Li, Hailan Ding, Chunwei Gong, Study on Tibetan Word Vector based on Word2vec, International Symposium on Power Electronics and Control Engineering (ISPECE), 2018 [https://iopscience.iop.org/article/10.1088/1742-6596/1187/5/052074/pdf pdf]
 +
# Lantian Li, Zhiyuan Tang, Dong Wang, Thomas Fang Zheng, FULL-INFO TRAINING FOR DEEP SPEAKER FEATURE LEARNING, ICASSP 2018.[https://arxiv.org/pdf/1711.00366 arXiv]
 +
# Lantian Li, Dong Wang*, Yixiang Chen, Ying Shing, Zhiyuan Tang, Thomas Fang Zheng, DEEP FACTORIZATION FOR SPEECH SIGNAL, ICASSP 2018 [https://arxiv.org/pdf/1803.00886 arXiv]
 +
# Dong Wang, Thomas Fang Zheng, Zhiyuan Tang, Ying Shi, Lantian Li, Shiyue Zhang Hongzhi Yu, Guanyu Li, Shipeng Xu, Askar Hummdulla, Mijit Ablimit, Gulnigar Mahmut, M2ASR: AMBITIONS AND FIRST YEAR PROGRESS, O-COCOSDA 2017. [[媒体文件:M2asr.pdf|pdf]]
 +
# Yang Feng, Shiyue Zhang, Andy Zhang, Dong Wang and Andrew Abel, Memory-augmented Neural Machine Translation, EMNLP 2017 [http://wangd.cslt.org/public/pdf/memory-augmented-nmt.pdf pdf]  
 +
# Lantian Li, Yixiang Chen, Dong Wang, Thomas Fang Zheng, A Study on Replay Attack and Anti-Spoofing for Automatic Speaker Verification, Interspeech 2017 [https://arxiv.org/pdf/1705.03670.pdf pdf]
 +
# Lantian Li, Yixiang Chen, Ying Shi, Zhiyuan Tang, Dong Wang, "Deep Speaker Feature Learning for Text-independent Speaker Verification", Interspeech 2017[https://arxiv.org/pdf/1705.03670.pdf pdf]
 +
# Jiyuan Zhang, Yang Feng, Dong Wang, Yang Wang, Andrw Abel, Shiyue Zhang, Andi Zhangi, "Flexible and Creative Chinese Poetry Generation Using Neural Memory", ACL 2017 [https://arxiv.org/abs/1705.03773 link]
 +
# Zhiyuan Tang, Ying Shi, Dong Wang, Yang Feng, and Shiyue Zhang, "Memory Visualization for Gated Recurrent Neural Networks in Speech Recognition", ICASSP 2017.[https://arxiv.org/abs/1609.08789 link]
 
# Zhiyuan Tang, Dong Wang, Yixiang Chen, Qing Chen, AP17-OLR Challenge: Data, Plan, and Baseline, APSIPA 2017, link: [https://arxiv.org/abs/1706.09742 arXiv]
 
# Zhiyuan Tang, Dong Wang, Yixiang Chen, Qing Chen, AP17-OLR Challenge: Data, Plan, and Baseline, APSIPA 2017, link: [https://arxiv.org/abs/1706.09742 arXiv]
 
# Shiyue Zhang, Gulnigar Mahmut, Dong Wang, Askar Hamdulla, Memory-augmented Chinese-Uyghur Neural Machine Translation, APSIPA 2017, link: [https://arxiv.org/abs/1706.08683 arXiv]  
 
# Shiyue Zhang, Gulnigar Mahmut, Dong Wang, Askar Hamdulla, Memory-augmented Chinese-Uyghur Neural Machine Translation, APSIPA 2017, link: [https://arxiv.org/abs/1706.08683 arXiv]  
第20行: 第68行:
 
# Dong Wang, Lantian Li, Zhiyuan Tang, Thomas Fang Zheng, Deep Speaker Verification: Do We Need End to End?, APSIPA 2017, link: [https://arxiv.org/abs/1706.07859 arXiv]
 
# Dong Wang, Lantian Li, Zhiyuan Tang, Thomas Fang Zheng, Deep Speaker Verification: Do We Need End to End?, APSIPA 2017, link: [https://arxiv.org/abs/1706.07859 arXiv]
 
# Miao Zhang, Yixiang Chen, Lantian Li and Dong Wang, Speaker Recognition with Cough, Laugh and “Wei”, APSIPA 2017, link: [https://arxiv.org/abs/1706.07860 arXiv]
 
# Miao Zhang, Yixiang Chen, Lantian Li and Dong Wang, Speaker Recognition with Cough, Laugh and “Wei”, APSIPA 2017, link: [https://arxiv.org/abs/1706.07860 arXiv]
 +
# Rehmutulla Memet; Mewlude Nijat; Gulnigar Mahmut; Askar Hamdulla, A rule and statistical modeling based stem extraction method for Kazakh words,Proceedings of the 2017 International Conference on Asian Language Processing, IALP 2017, v 2018-January, p 231-234, July 2, 2017 [https://ieeexplore.ieee.org/abstract/document/8300586 link]
 +
# Shipeng Xu, Hongzhi Yu, Thomas Fang Zheng, Guanyu Li, Gegeentana. “Language Resource Construction for Mongolian”, Proceedings of APSIPA Annual Summit and Conference(APSIPA), 2017 [https://ieeexplore.ieee.org/abstract/document/8282132 pdf]
  
==Submissions==
+
==Other papers==
 
+
# 沙尔旦尔·帕尔哈提,米吉提·阿不里米提,艾斯卡尔·艾木都拉. 基于稳健词素序列和LSTM的维吾尔语短文本分类[J]. 中文信息学报,2020,34(01):63-70. [http://jcip.cipsc.org.cn/CN/article/downloadArticleFile.do?attachType=PDF&id=2894 link]
===TASLP===
+
# 沙尔旦尔·帕尔哈提,米吉提·阿不里米提,艾斯卡尔·艾木都拉. 词干单元和卷积神经网络的哈萨克短文本分类[J]. 小型微型计算机系统,2020,41(08):1627-1633. [http://gb.oversea.cnki.net/KCMS/detail/detail.aspx?filename=XXWX202008014&dbcode=CJFD&dbname=CJFDTEMP link]
Dong Wang, Lantian Li, Yixiang Chen, Ying Shi, Zhiyuan Tang and Thomas Fang Zheng, Learning Deep Speaker Features
+
 
+
===OCOCOSDA 2017===
+
 
+
*Title: M2ASR: AMBITIONS AND FIRST YEAR PROGRESS
+
:Author: Dong Wang, Thomas Fang Zheng, Zhiyuan Tang, Ying Shi, Lantian Li, Shiyue Zhang Hongzhi Yu, Guanyu Li, Shipeng Xu, Askar Hummdulla, Mijit Ablimit, Gulnigar Mahmut
+
:link: [[媒体文件:M2asr.pdf|pdf]]
+

2022年1月7日 (五) 13:10的最后版本

Journal papers (SCI)

  1. Lantian Li, Ruiqi Liu, Jiawen Kang, Yue Fa, Hao Cui, Yunqi Cai, Ravichander Vipperla, Thomas Fang Zheng and Dong Wang. "CN-Celeb: multi-genre speaker recognition", Speech Communication, 2022. pdf
  2. Lantian Li, Dong Wang etc., A Principle Solution for Enroll-Test Mismatch, IEEE Transaction on Audio, Speech and Language Processing, 2021 pdf
  3. Yunqi Cai, Lantian Li, Andrew Abel, Xiaoyan Zhu, Dong Wang, "Deep Normalization for Speaker Vectors", IEEE Transactions on Audio, Speech and Language Processing, 2020. pdf
  4. Dong Wang, "A Simulation Study on Optimal Scores for Speaker Recognition", EURASIP Journal on Audio, Speech, and Music Processing, 2020. pdf
  5. Gulnur Arkin, Askar Hamdulla and Mijit Ablimit , Analysis of phonemes and tones confusion rules obtained by ASR,Wireless Networks,2020.link
  6. Zhiyuan Tang, Lantian Li, Dong Wang, Ravichander Vipperla, "Collaborative Joint Training With Multitask Recurrent Model for Speech and Speaker Recognition", IEEE Transactions on Audio, Speech and Language Processing 2018, vol 25, no.3. online
  7. Zhiyuan Tang,Dong Wang,Yixiang Chen,Lantian Li,Andrew Abel, "Phonetic Temporal Neural Model for Language Identification", IEEE Transactions on Audio, Speech and Language Processing 2017. online

Journal papers (EI)

  1. Siamese Attention-based LSTM for Speech Emotion Recognition,IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, v E103A, n 7, p 937-941, July 1, 2020 link
  2. Uyghur short-text classification based on reliable sub-word morphology, International Journal of Reasoning-based Intelligent Systems,v 11, n 3, p 250-255, 2019 link
  3. A Robust Morpheme Sequence and Convolutional Neural Network-Based Uyghur and Kazakh Short Text Classification, Information (Switzerland), v 10, n 12, December 1, 2019 pdf


Conference papers (EI)

  1. Tiankai Zhi, Ying Shi, Wenqiang Du, Guanyu Li and Dong Wang, "A Free Mongolian Speech Database and Accompanied Baselines", O-COCOSDA 2021.[]
  2. Jiao Han, Yunqi Cai, Lantian Li, Guanyu Li, Dong Wang, "An MAP Estimation for Between-Class Variance", APSIPA 2021. []
  3. Di Wang, Lantian Li, Hongzhi Yu, Dong Wang,A STUDY ON DECOUPLED PROBABILISTIC LINEAR DISCRIMINANT ANALYSIS, APSIPA 2021.
  4. Haoran Sun, Lantian Li, Thomas Fang Zheng, Dong Wang, HOW SPEECH IS RECOGNIZED TO BE EMOTIONAL - A STUDY BASED ON INFORMATION DECOMPOSITION, APSIPA 2021.
  5. Lantian Li, Yang Zhang, Jiawen Kang, Thomas Fang Zheng, Dong Wang, "SQUEEZING VALUE OF CROSS-DOMAIN LABELS: A DECOUPLED SCORING APPROACH FOR SPEAKER VERIFICATION", ICASSP 2021. [pdf]
  6. Ying Shi, Haolin Chen, Zhiyuan Tang, Lantian Li, Dong Wang, Jiqing Han, Can We Trust Deep Speech Prior?, SLT 2021pdf pdf
  7. Zheng Li, Miao Zhao, Qingyang Hong, Lin Li, Zhiyuan Tang, Dong Wang, Liming Song, Cheng Yang, "AP20-OLR Challenge: Three Tasks and TheirBaselines", APSIPA 2020. pdf
  8. Jiawen Kang,Ruiqi Liu,Lantian Li,Yunqi Cai,Dong Wang,Thomas Fang Zheng, "Domain-Invariant Speaker Vector Projection by Model-Agnostic Meta-Learning", Interspeech 2020. pdf
  9. Sitong Cheng,Zhixin Liu,Lantian Li,Zhiyuan Tang,Dong Wang,Thomas Fang Zheng, "ASR-Free Pronunciation Assessment", Interspeech 2020. pdf
  10. Lantian Li,Dong Wang,Thomas Fang Zheng, "Neural Discriminant Analysis for Deep Speaker Embedding", Interspeech 2020. pdf
  11. Yongmin Li, Guanyu Lia, Pengqi Lia, Sixuan Lia, Xinyu Yuan, ”A Survey of Multimodal Fusion for Identity Verification”, International Symposium on Electronic Information Technology and Communication Engineering(ISEITCE), 2020 pdf
  12. Yue Fan, Jiawen Kang, Lantian Li, Kaicheng Li, Haolin Chen, Sitong Cheng, Pengyuan Zhang, Ziya Zhou, Yunqi Cai, Dong Wang, "CN-CELEB: A Challenging Chinese Speaker Recognition Dataset", ICASSP 2020. pdf
  13. Wupeng Wang, Chao Xing, Dong Wang, Xiao Chen, Fengyu Sun, "A ROBUST AUDIO-VISUAL SPEECH ENHANCEMENT MODEL", ICASSP 2020, pdf
  14. Yang Zhang and Lantian Li and Dong Wang, "VAE-based regularization for deep speaker embedding", Interspeech 2019 pdf
  15. Lantian Li,Zhiyuan Tang,Ying Shi,Dong Wang, "Gaussian-Constrained Training for Speaker Verification", ICASSP 2019pdf
  16. Sardar Parhat, Gao Ting, Mijit Ablimit, Askar Hamdulla, A morpheme sequence and convolutional neural network based Kazakh text classification,2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019, p 1903-1906, November 2019 pdf
  17. Arkin G, Alijan G, Hamdulla A, A Comparative Analysis of Acoustic Characteristics between Kazak Uyghur Mandarin Learners and Standard Mandarin Speakers,Proceedings of the 2019 International Conference on Asian Language Processing, IALP 2019, p 474-479, November 2019 link
  18. Statistical Analysis of Syllable Duration of Uyghur Language,Proceedings of the 2019 International Conference on Asian Language Processing, IALP 2019, p 468-473, November 2019 [1]
  19. Lantian Li,Zhiyuan Tang,Ying Shi,Dong Wang, "Phonetic-Attention Scoring for Deep Speaker Features in Speaker Verification", APSIPA 2019 pdf
  20. Lantian Li*,Xueyi Wang*,Dong Wang, "VAE-based Domain Adaptation for Speaker Verification", APSIPA 2019. pdf
  21. Jiayao Wu, Zhiyuan Tang and Dong Wang, "Structure Growth for Small-Footprint Speech Recognition", APSIPA 2019. pdf
  22. Zhiyuan Tang, Dong Wang, Liming Song, "AP19-OLR Challenge: Three Tasks and Their Baselines", APSIPA 2019. pdf
  23. Yunqi Cai, Dong Wang, "Question Mark Prediction By Bert", APSIPA 2019 pdf
  24. Guanyu Li, Lisai Luo, Chunwei Gong, Shiliang Lv, “End-to-end Tibetan Speech Synthesis Based on Phones and Semi-syllables”, Proceedings of APSIPA Annual Summit and Conference(APSIPA) 2019 pdf
  25. Duo Ma, Guanyu Li, Haihua Xu, Eng Siong Chng, “Improving code-switching speech recognition with data augmentation and system combination”, Proceedings of APSIPA Annual Summit and Conference(APSIPA) 2019 [2]
  26. Jiyuan Zhang,Dong Wang, "Chinese Poetry Generation with Flexible Styles", ISCSLP 2018pdf.
  27. Jiyuan Zhang,Zheling Zhang,Shiyue Zhang, Dong Wang,"VV-COUPLET: AN OPEN SOURCE CHINESE COUPLET GENERATION SYSTEM", APSIPA 2018. pdf
  28. Zhiyuan Tang,Dong Wang,Qing Chen, "AP18-OLR CHALLENGE: THREE TASKS AND THEIR BASELINES",APSIPA 2018.pdf
  29. Ying Shi,Zhiyuan Tang, Lantian Li,Zheling Zhang,Dong Wang, "MAP AND RELABEL: TOWARDS ALMOST-ZERO RESOURCE SPEECH RECOGNITION",APSIPA 2018.pdf
  30. Miao Zhang, Xiaofei Kang, Yanqing Wang, Lantian Li, Zhiyuan Tang, Haisheng Dai, Dong Wang*, HUMAN AND MACHINE SPEAKER RECOGNITION BASED ON SHORT TRIVIAL EVENT, ICASSP 2018 arXiv
  31. Jinghao Yan, Hongzhi Yu, Guanyu Li,"Tibetan acoustic model research based on TDNN", APSIPA ASC 2018 pdf
  32. Yultuz Rapkat; Gulnur Arkin; Mijit Ablimit; Askar Hamdulla, Acoustic Features of Mandarin Diphthongs by Uyghur Learners at Primary Level,2018 Oriental COCOSDA - International Conference on Speech Database and Assessments, ICSDA 2018 - Proceedings, p 60-66, July 2, 2018, link
  33. Mijit Ablimit*, Sardar Parhat*, Askar Hamdulla*, Thomas Fang Zheng, Multilingual Stemming and Term extraction for Uyghur, Kazak and Kirghiz,2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings, p 587-590, July 2, 2018 pdf
  34. Lisai Luo, Guanyu Li1, Chunwei Gong, Hailan Ding, “End-to-end Speech Synthesis for Tibetan Lhasa Dialect”, International Symposium on Power Electronics and Control Engineering (ISPECE), 2018 pdf
  35. Ning Yang, Guanyu Li, Hailan Ding, Chunwei Gong, Study on Tibetan Word Vector based on Word2vec, International Symposium on Power Electronics and Control Engineering (ISPECE), 2018 pdf
  36. Lantian Li, Zhiyuan Tang, Dong Wang, Thomas Fang Zheng, FULL-INFO TRAINING FOR DEEP SPEAKER FEATURE LEARNING, ICASSP 2018.arXiv
  37. Lantian Li, Dong Wang*, Yixiang Chen, Ying Shing, Zhiyuan Tang, Thomas Fang Zheng, DEEP FACTORIZATION FOR SPEECH SIGNAL, ICASSP 2018 arXiv
  38. Dong Wang, Thomas Fang Zheng, Zhiyuan Tang, Ying Shi, Lantian Li, Shiyue Zhang Hongzhi Yu, Guanyu Li, Shipeng Xu, Askar Hummdulla, Mijit Ablimit, Gulnigar Mahmut, M2ASR: AMBITIONS AND FIRST YEAR PROGRESS, O-COCOSDA 2017. pdf
  39. Yang Feng, Shiyue Zhang, Andy Zhang, Dong Wang and Andrew Abel, Memory-augmented Neural Machine Translation, EMNLP 2017 pdf
  40. Lantian Li, Yixiang Chen, Dong Wang, Thomas Fang Zheng, A Study on Replay Attack and Anti-Spoofing for Automatic Speaker Verification, Interspeech 2017 pdf
  41. Lantian Li, Yixiang Chen, Ying Shi, Zhiyuan Tang, Dong Wang, "Deep Speaker Feature Learning for Text-independent Speaker Verification", Interspeech 2017pdf
  42. Jiyuan Zhang, Yang Feng, Dong Wang, Yang Wang, Andrw Abel, Shiyue Zhang, Andi Zhangi, "Flexible and Creative Chinese Poetry Generation Using Neural Memory", ACL 2017 link
  43. Zhiyuan Tang, Ying Shi, Dong Wang, Yang Feng, and Shiyue Zhang, "Memory Visualization for Gated Recurrent Neural Networks in Speech Recognition", ICASSP 2017.link
  44. Zhiyuan Tang, Dong Wang, Yixiang Chen, Qing Chen, AP17-OLR Challenge: Data, Plan, and Baseline, APSIPA 2017, link: arXiv
  45. Shiyue Zhang, Gulnigar Mahmut, Dong Wang, Askar Hamdulla, Memory-augmented Chinese-Uyghur Neural Machine Translation, APSIPA 2017, link: arXiv
  46. Shipeng Xu , Hongzhi Yu, Thomas Fang Zheng and Jinghao Yan, Language Resource Construction for Mongolian, APSIPA 2017, pdf
  47. Guanyu Li, Hongzhi Yu, Thomas Fang Zheng, Jinghao Yan, Free Linguistic and Speech Resources for Tibetan, APSIPA 2017, link: pdf
  48. Ying Shi, Askar Hamdulla, Zhiyuan Tang, Dong Wang, Thomas Fang Zheng, A Free Kazak Speech Database and a Speech Recognition Baseline, APSIPA 2017, link: pdf
  49. Mijit Ablimit, Sardar Parhat, Askar Hamdulla, Thomas Fang Zheng , A Multilingual Language Processing Tool for Uyghur, Kazak and Kirghiz, APSIPA 2017, link: pdf
  50. Aodong Li, Shiyue Zhangy, Dong Wangz and Thomas Fang Zheng, Enhanced Neural Machine Translation by Learning from Draft, APSIPA 2017, link: pdf
  51. Lantian Li, Dong Wang, Askar Rozi, Thomas Fang Zheng, Cross-lingual Speaker Verification with Deep Feature Learning, APSIPA 2017, link: arXiv
  52. Dong Wang, Lantian Li, Zhiyuan Tang, Thomas Fang Zheng, Deep Speaker Verification: Do We Need End to End?, APSIPA 2017, link: arXiv
  53. Miao Zhang, Yixiang Chen, Lantian Li and Dong Wang, Speaker Recognition with Cough, Laugh and “Wei”, APSIPA 2017, link: arXiv
  54. Rehmutulla Memet; Mewlude Nijat; Gulnigar Mahmut; Askar Hamdulla, A rule and statistical modeling based stem extraction method for Kazakh words,Proceedings of the 2017 International Conference on Asian Language Processing, IALP 2017, v 2018-January, p 231-234, July 2, 2017 link
  55. Shipeng Xu, Hongzhi Yu, Thomas Fang Zheng, Guanyu Li, Gegeentana. “Language Resource Construction for Mongolian”, Proceedings of APSIPA Annual Summit and Conference(APSIPA), 2017 pdf

Other papers

  1. 沙尔旦尔·帕尔哈提,米吉提·阿不里米提,艾斯卡尔·艾木都拉. 基于稳健词素序列和LSTM的维吾尔语短文本分类[J]. 中文信息学报,2020,34(01):63-70. link
  2. 沙尔旦尔·帕尔哈提,米吉提·阿不里米提,艾斯卡尔·艾木都拉. 词干单元和卷积神经网络的哈萨克短文本分类[J]. 小型微型计算机系统,2020,41(08):1627-1633. link