Xiao-Lei Zhang's Homepage

1. School of Marine Science and Technology, Northwestern Polytechnical University, China

2. Research and Development Institute of Northwestern Polytechnical University in Shenzhen, China

Address: 127 Youyi West Road, Beilin District, Xi'an, Shaanxi 710072, China.

Audio and Speech Processing, Machine Learning, Statistical Signal Processing, Artificial Intelligence.

Xiao-Lei Zhang received the Ph.D. degree with honors from the Information and Communication Engineering, Tsinghua University, Beijing, China, in 2012. He was a postdoctoral researcher with the Department of Electronic Engineering, Tsinghua University from 2012 to 2014. He was a visiting scholar with the Perception and Neurodynamics Laboratory,The Ohio State University, Columbus, OH, USA from 2013 to 2014. He was a postdoctoral researcher with the Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA from 2014 to 2016. Since 2016, he joint the Northwestern Polytechnical University, Xi'an, China, where he is currently a full professor.

His research interests are the topics in speech processing, machine learning, statistical signal processing, and artificial intelligence. He has published numerous peer-reviewed articles in journals and conference proceedings including IEEE TPAMI, IEEE TASLP, IEEE TCYB, IEEE TSMC, Neural Networks, Pattern Recognition, Computer Speech and Language, Speech Communication, etc. He has authored a book 'speech signal processing based on deep learning in adverse environments', and co-authored a text book in statistics.

He received the 2020 Neural Networks Best Paper Award from the International Neural Network Society, the Excellent Paper Award Winner of Ubi-Media 2019 (with Mou Wang and Susanto Rahardja), the First-class Beijing Science and Technology Award in 2014, He was an APSIPA Distinguished Lecturer in 2018-2019. He was selected into the Youth Program of National Distinguished Experts of China in 2017, and the Hundred Talents Plan of Shaanxi Province of China, in 2017.

He serves/served an action editor of Neural Networks, an associate editor of IEEE/ACM Transactions on Audio, Speech, and Language Processing, EURASIP Journal on Audio, Speech, and Music Processing, and many other journals, and helps organized many conferences and challenges. He is an elected member of the IEEE SPS Speech and Language Processing Technical Committee (SLTC) (2021-2023), and an elected vice chairman of the Speech Information Technical Committee of the Chinese Information Processing Society of China (2023-). He is a senior member of IEEE, a member of the IEEE SPS, ISCA, CAA, CAAI, CCF, CIPS, etc.

Publications

Books　

张晓雷(著). 复杂环境下语音信号处理的深度学习方法. 清华大学出版社, 2021年12月. ISBN:9787302590002. [Xiao-Lei Zhang. Speech signal processing based on deep learning in adverse environments. Tsinghua University Press, December 2021. (in chinese)]

Journal articles

Lei Zhao, Wenbo Zhu, Shengqiang Li, Hong Luo, Xiao-Lei Zhang, and Susanto Rahardja, “Multi-resolution convolutional residual neural networks for monaural speech dereverberation,'' IEEE/ACM Transactions on Audio, Speech, and Language Processing (IEEE TASLP), volume X, pages X-X, 2024.
Jiadi yao, Hong Luo, Jun Qi, and Xiao-Lei Zhang, “Interpretable spectrum transformation attacks to speaker recognition,'' IEEE/ACM Transactions on Audio, Speech, and Language Processing (IEEE TASLP), volume 32, pages 1531-1545, 2024.[code]
Xueqing Li, Shengqiang Li, Xiao-Lei Zhang, and Susanto Rahardja, "Transformer-based end-to-end speech translation with rotary position embedding," IEEE Signal Processing Letters (IEEE SPL), volume 31, pages 371-375, 2024.
Jie Wang, Xing Chen, and Xiao-Lei Zhang, “Zeroth and first-order difference discrimination for unsupervised domain adaptation,” Complex & Intelligent Systems, 2023.
Xing Chen, Jie Wang, Xiao-Lei Zhang, Wei-Qiang Zhang, and Kunde Yang, "LMD: A learnable mask network to detect adversarial examples for speaker verification," IEEE/ACM Transactions on Audio, Speech, and Language Processing (IEEE TASLP), volume 31, pages 2476-2490, 2023.
Jie Wang and Xiao-Lei Zhang, “Improving pseudo labels with intra-class similarity for unsupervised domain adaptation,” Pattern Recognition, volume 138, number 109379, pages 1-11, 2023.
Jiadi Yao, Chengdong Liang, Xing Chen, Xiao-Lei Zhang, Wei-Qiang Zhang, and Kunde Yang, “Symmetric saliency-based adversarial attack to speaker identification,” IEEE Signal Processing Letters (IEEE SPL), volume 30, pages 1-5, 2023.
Mou Wang, Junqi Chen, Xiao-Lei Zhang, and Susanto Rahardja, “End-to-end multi-modal speech recognition on an air and bone conducted speech corpus,” IEEE/ACM Transactions on Audio, Speech, and Language Processing (IEEE TASLP), volume 31, pages 513-524, 2023.
Xiao-Lei Zhang, Lei Xie, Eric Fosler-Lussier, Emmanuel Vincent, “Special issue on advances in deep learning based speech processing,” Neural Networks (NNJ), volume 158, pages 328-330, 2023.
Jianyu Wang and Xiao-Lei Zhang, “Deep NMF topic modeling,” Neurocomputing, volume 515, pages 157-173, 2023.
Xiao-Lei Zhang and Menglong Xu, “AUC optimization for deep learning based voice activity detection,” EURASIP Journal on Audio, Speech, and Music Processing, volume 2022, pages 1-12, 2022.
Mou Wang, Junqi Chen, Xiao-Lei Zhang, Zhiyong Huang, and Susanto Rahardja. “Multi-modal speech enhancement with bone-conducted speech in time domain.” Applied Acoustics, volume 200, number 109058, pages, 2022.
Qian Wang, Mou Wang, Yan Yang, and Xiaolei Zhang, “Multi-modal emotion recognition using EEG and speech signals,” Computers in Biology and Medicine, volume 105907, pages 1-16, 2022.
Ziye Yang, Shanzheng Guan, and Xiao-Lei Zhang. “Deep ad-hoc beamforming based on speaker extraction for target-dependent speech separation,” Speech Communication, volume 140, pages 87-97, 2022.
Zhongxin Bai, Jianyu Wang, Xiao-Lei Zhang, and Jingdong Chen “End-to-end speaker verification via curriculum bipartite ranking weighted binary cross-entropy,” IEEE/ACM Transactions on Audio, Speech, and Language Processing (IEEE TASLP), volume 30, pages 1330-1344, 2022.
Jianyu Wang, Shanzheng Guan, Shupei Liu, and Xiao-Lei Zhang. Minimum-volume multichannel nonnegative matrix factorization for blind audio source separation. IEEE/ACM Transactions on Audio, Speech, and Language Processing (IEEE TASLP), volume 29, pages 3089-3103, 2021.
Zhongxin Bai and Xiao-Lei Zhang. Speaker recognition based on deep learning: An overview. Neural Networks (NNJ), volume 140, pages 65-99, 2021.
Xiao-Lei Zhang. Deep ad-hoc beamforming. Computer Speech and Language, volume 68, number 101201, pages 1-18, 2021 (arXiv preprint arXiv:1811.01233, 6th November 2018, last revised on 7th January 2019.) [arXiv]
Mou Wang, Xiao-Lei Zhang, and Susanto Rahardja. An unsupervised deep learning system for acoustic scene analysis. Applied Sciences, volume 10, number 6, pages 2076-2080, 2020.
Zhongxin Bai, Xiao-Lei Zhang, and Jingdong Chen. Speaker verification by partial AUC optimization with Mahalanobis distance metric learning. IEEE/ACM Transactions on Audio, Speech, and Language Processing (IEEE TASLP), volume 28, pages 1533-1548, 2020.
Zhongxin Bai, Xiao-Lei Zhang, and Jingdong Chen. Cosine metric learning based speaker verification. Speech Communication, volume 118, pages 10--20, 2020
Naijun Zheng and Xiao-Lei Zhang. Phase-aware speech enhancement based on deep neural networks. IEEE/ACM Transactions on Audio, Speech, and Language Processing (IEEE TASLP), volume 27, number 1, pages 63-76, 2019.
Xiao-Lei Zhang. Multilayer bootstrap networks. Neural Networks (NNJ), volume 103, pages 29-43, 2018. [arXiv][project page] (recepient of the 2020 Best Paper Award from journal Neural Networks and International Neural Network Society)
Xiao-Lei Zhang and DeLiang Wang. A deep ensemble learning method for monaural speech separation. IEEE/ACM Transactions on Audio, Speech, and Language Processing (IEEE TASLP), volume 24, number 5, pages 967-977, 2016. [supplement]
Xiao-Lei Zhang and DeLiang Wang. Boosting contextual information for deep neural network based voice activity detection. IEEE/ACM Transactions on Audio, Speech, and Language Processing (IEEE TASLP), volume 24, number 2, pages 252-264, February 2016. [supplement][example_of_automatic_labeling (6.0MB)]
Xiao-Lei Zhang. Heuristic ternary error correcting output codes via weight optimization and layered clustering-based approach. IEEE Transactions on Cybernetics (IEEE TCYB), volume 45, number 2, pages 289-301, February 2015.
Xiao-Lei Zhang. Convex discriminative multitask clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), volume 37, number 1, pages 28-40, January, 2015.[supplement]
Xiao-Lei Zhang and Ji Wu. Deep belief networks based voice activity detection. IEEE Transactions on Audio, Speech, and Language Processing (IEEE TASLP), volume 21, number 4, pages 697-710, April 2013.
Xiao-Lei Zhang and Ji Wu. Linearithmic time sparse and convex maximum margin clustering. IEEE Transactions on Systems, Man, and Cybernetics—Part B: Cybernetics (IEEE TSMCB), volume 42, number 6, pages 1669-1692, December 2012.
Ji Wu and Xiao-Lei Zhang, Efficient multiple kernel support vector machine based voice activity detection, IEEE Signal Processing Letters (IEEE SPL), volume 18, number 8, pages 466-469, August 2011.
Ji Wu and Xiao-Lei Zhang, An efficient voice activity detection algorithm by combining statistical model and energy detection, EURASIP Journal on Advances in Signal Processing, volume 2011, number 1, pages 18-27, July 2011.
Ji Wu and Xiao-Lei Zhang, Maximum margin clustering based statistical VAD with multiple observation compound feature, IEEE Signal Processing Letters (IEEE SPL), volume 18, number 5, pages 283-286, May 2011.

Conference papers

Xianyan Fu, Xiao-Lei Zhang, Chao-Han Huck Yang, and Jun Qi, "Exploiting a quantum multiple kernel learning approach for low-resource spoken command recognition,'' In Proceedings of the 2024 IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP'24), Seoul, Korea, April 2024, pages XX-XX.
Lei Zhao and Xiao-Lei Zhang, "A hierarchical multi-proxy loss with dynamic main-proxy for deep metric learning,'' In Proceedings of the 2024 IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP'24), Seoul, Korea, April 2024, pages XX-XX.
Jiadi Yao, Chengdong Liang, Zhendong Peng, Binbin Zhang, and Xiao-Lei Zhang, “Branch-ECAPA-TDNN: A parallel branch architecture to capture local and global features for speaker verification,” In Proceedings of Interspeech, Dublin, Ireland, August 2023, pages 1943-1947.
Jie Wang, Menglong Xu, Jingyong Hou, Binbin Zhang, Xiao-Lei Zhang, Lei Xie, and Fuping Pan, “WeKws: A production first small-footprint end-to-end Keyword Spotting Toolkit,” In Proceedings of the 47th IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP’23), Rhodes Is- land, Greece, June 2023.
Linfeng Feng, Yijun Gong, and Xiao-Lei Zhang, “Soft label coding for end-to-end sound source localization with ad-hoc microphone arrays,” In Proceedings of the 47th IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP’23), Rhodes Island, Greece, June 2023.
Jun Qi, Xiao-Lei Zhang, and Javier Tejedor, “Optimizing quantum federated learning based on federated quantum natural gradient descent,” In Proceedings of the 47th IEEE International Conference onAcoustic, Speech, and Signal Processing (ICASSP’23), Rhodes Island, Greece, June 2023.
Chengdong Liang, Xiao-Lei Zhang, BinBin Zhang, Di Wu, Shengqiang Li, Xingchen Song, Zhendong Peng, and Fuping Pan, “Fast-U2++: Fast and Accurate End-to-End Speech Recognition in Joint CTC/Attention Frames,” In Proceedings of the 47th IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP’23), Rhodes Island, Greece, June 2023.
Xing Chen, Jiadi Yao, and Xiao-Lei Zhang, “Masking speech feature to detect adversarial examples for speaker verification,” In Proceedings of Asia-Pacific Signal and Information Processing Association (APSIPA ASC’22), Chiang Mai, Thailand, November 2022, pages 191-195
Yijun Gong, Shupei Liu, and Xiao-Lei Zhang, “End-to-end two-dimensional sound source localization with ad-hoc microphone arrays,” In Proceedings of Asia-Pacific Signal and Information Processing Association (APSIPA ASC’22), Chiang Mai, Thailand, November 2022, pages 1944-1949.
Menglong Xu, Shengqiang Li, Chengdong Liang, and Xiao-Lei Zhang. “Multiclass AUC optimization for robust small-footprint keyword spotting with limited training data,” In Proceedings of Interspeech, Incheon, Korea, September 2022, pages 3278-3282.
Chengdong Liang, Yijiang Chen, Jiadi Yao, and Xiao-Lei Zhang. “Multi-Channel Far-Field Speaker Verification with Large-Scale Ad-hoc Microphone Arrays,” In Proceedings of Interspeech, Incheon, Korea, September 2022, pages 3679-3683.
Yijun Gong and Xiao-Lei Zhang. “DP-Means: an efficient Bayesian nonparametric model for speaker diarization,” In Odyssey Workshop, Beijing, China, June 2022, pages 156-161.
Junqi Chen, Mou Wang, Xiao-Lei Zhang, Zhiyong Huang, and Susanto Rahardja. “End-to-end multi-modal speech recognition with air and bone conducted speech.” In Proceedings of the 46th IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP'22), Singapore, Singapore, May 2022, pages 6052-6056.
Wenbo Zhu, Mou Wang, Xiao-Lei Zhang, and Susanto Rahardja. A comparison of handcrafted, parameterized, and learnable features for speech separation. In Proceedings of Asia-Pacific Signal and Information Processing Association (APSIPA ASC'21), Tokyo, Japan, December 2021, pages 635-639.
Shengqiang Li, Menglong Xu, and Xiao-Lei Zhang. Efficient conformer-based speech recognition with linear attention. In Proceedings of Asia-Pacific Signal and Information Processing Association (APSIPA ASC'21), Tokyo, Japan, December 2021, pages 448-453.
Shengqiang Li, Menglong Xu, and Xiao-Lei Zhang. Conformer-based end-to-end speech recognition with rotary position embedding. In Proceedings of Asia-Pacific Signal and Information Processing Association (APSIPA ASC'21), Tokyo, Japan, December 2021, pages 443-447.
Shanzheng Guan, Shupei Liu, Junqi Chen, Wenbo Zhu, Shengqiang Li, Xu Tan, Ziye Yang, Menglong Xu, Yijiang Chen, Chengdong Liang, Jianyu Wang, and Xiao-Lei Zhang. Libri-adhoc40: A dataset collected from synchronized ad-hoc microphone arrays. In Proceedings of Asia-Pacific Signal and Information Processing Association (APSIPA ASC'21), Tokyo, Japan, December 2021, pages 1116-1120.
Chengdong Liang, Junqi Chen, Shanzheng Guan, and Xiao-Lei Zhang. Attention-based multi-channel speaker verification with ad-hoc microphone arrays. In Proceedings of Asia-Pacific Signal and Information Processing Association (APSIPA ASC'21), Tokyo, Japan, December 2021, pages 1111-1115.
Jianyu Wang, Shanzheng Guan, and Xiao-Lei Zhang. Minimum-volume regularized ILRMA for blind audio source separation. In Proceedings of Asia-Pacific Signal and Information Processing Association (APSIPA ASC'21), Tokyo, Japan, December 2021, pages 630-634.
Junqi Chen and Xiao-Lei Zhang. Scaling sparsemax based channel selection for speech recognition with ad-hoc microphone arrays. In Proceedings of Interspeech, Brno, Czech Republic, September 2021, pages 291-295.
Xu Tan and Xiao-Lei Zhang. Speech enhancement aided end-to-end multi-task learning for voice activity detection. In Proceedings of the 45th IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP 2021), Toronto, Ontario, Canada, June 2021, pages 6823-6827.
Menglong Xu, Shengqiang Li, and Xiao-Lei Zhang. Transformer-based end-to-end speech recognition with local dense synthesizer attention. In Proceedings of the 45th IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP 2021), Toronto, Ontario, Canada, June 2021, pages 5899-5903.
Ziye Yang, Xiao-Lei Zhang, and Zhonghua Fu. Multi-channel speech separation using deep embedding with multilayer bootstrap networks. In Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2020), Auckland, New Zealand, December 2020, pages 716-719.
Menglong Xu and Xiao-Lei Zhang. Depthwise separable convolutional ResNet with squeeze-and-excitation blocks for small-footprint keyword spotting. In Proceedings of Interspeech, Shanghai, China, October 2020, pages 2547-2551.
Jian-Yu Wang and Xiao-Lei Zhang. Deep topic modeling by multilayer bootstrap networks and lasso. In Proceedings of the 25th IEEE International Conference on Pattern Recognition (ICPR 2020), Milan, Italy, January 2021, pages 2470-2475.
Zhongxin Bai, Xiao-Lei Zhang, and Jingdong Chen. Partial AUC metric learning based speaker verification back-end. In Proceedings of the Odyssey Workshop (Odyssey 2020), Tokyo Japan, November 2020, pages 380-384. (one of the three inaugural Jack Godfrey's Best Student Paper Award Finallists)
Zhongxin Bai, Xiao-Lei Zhang, and Jingdong Chen. Partial AUC optimization based deep speaker embeddings with class-center learning for text-independent speaker verification. In Proceedings of the 44th IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP 2020), Virtual Barcelona, May 2020, pages 6819-6823.
Mou Wang, Rui Wang, Xiao-Lei Zhang, and Susanto Rahardja. A Hybrid constant-Q transform based CNN ensemble for acoustic scene classification. In Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2019), Lanzhou, China, November 2019, pages 205-209.
Rui Wang, Mou Wang, Xiao-Lei Zhang, and Susanto Rahardja. Domain adaptation neural network for acoustic scene classification in mismatched conditions. In Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2019), Lanzhou, China, November 2019, pages 1501-1505.
Ziye Yang and Xiao-Lei Zhang. Boosting spatial information for deep learning based multichannel speaker-independent speech separation in reverberant environments. In Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2019), Lanzhou, China, November 2019, pages 1506-1510.
Mou Wang, Xiao-Lei Zhang, and Susanto Rahardja. A hybrid approach for mobile phone clustering with speech recordings. In Proceedings of the 12th International Conference on Ubi-Media Computing (Ubi-Media 2019), Bali, Indonesia, 2019, pages 205-209. (Excellent Paper Award Winner)
Jingli Xie, Danqi Jin, Wen Zhang, Xiao-Lei Zhang, Jie Chen, and DeLiang Wang. Robust sparse multichannel active noise control. In Proceedings of the 44th IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP 2019), Brighton, United Kingdom, May 2019, pages 521-525.
Zi-Chen Fan, Zhongxin Bai, Xiao-Lei Zhang, Susanto Rahardja, and Jingdong Chen. AUC optimization for deep learning based voice activity detection. In Proceedings of the 44th IEEE International Conference on Acoustic, Speech, and Signal Processing (ICASSP 2019), Brighton, United Kingdom, May 2019, pages 6760-6764.
Menghzhen Li and Xiao-Lei Zhang, An Investigation of Speaker Clustering Algorithms in Adverse Acoustic Environments, In Proceedings of Asia-Pacific Signal and Information Processing Association (APSIPA ASC 2018), Honolulu, Hawaii, November 2018, pages 1462-1466.

Special issue on Deep Learning applied to Music Signal Processing, in EURASIP Journal on Audio, Speech, and Music Processing

Important Dates
Submission deadline: ~~1 September 2022~~ 31 January 2023

Lead Guest Editor
Xiaolei Zhang, Northwestern Polytechnical University
Email: xiaolei.zhang@nwpu.edu.cn

Guest Editors
Wenwu Wang, University of Surrey, UK
Ivan Lee, University of South Australia, Australia

Important: Authors should select "Deep Learning applied to Music Signal Processing" when they reach the “Article Type” step in the submission system.

1) Multiple post-doc positions at Northwestern Polytechnical University (NWPU) majoring in machine learning, deep learning, audio and speech processing, and language processing are available.

2) Multiple faculty positions at NWPU at levels of assistant professors, associate professors, and full professors are available.

Special issue on Deep Learning applied to Music Signal Processing, in EURASIP Journal on Audio, Speech, and Music Processing