Lei Xie

Ph.D, Professor, Senior Member IEEE

Audio, Speech & Language Processing Group (ASLP@NPU)

Shaanxi Provincial Key Laboratory of Speech & Image Information Processing (SAIIP)

School of Computer Science, Northwestern Polytechnical University, Xi'an, China

E-mail: lxie (at) nwpu.edu.cn, xielei21st (at) gmail.com, lxie (at) nwpu-aslp.org (Convert AT to @)

Biosketch

Dr. Lei Xie is currently a Professor in the Audio, Speech & Language Processing Group (ASLP), Shaanxi Provincial Key Laboratory of Speech & Image Information Processing, School of Computer Science, Northwestern Polytechnical Univeristy. Dr. Xie obtained his Ph.D. degree in Computer Science from Northwestern Polytechnical University, China in 2004. From 2001 to 2002, he has worked with Professor Hichem Sahli at the Department of Electronics and Informatics, Vrije Universiteit Brussel (VUB), Brussels, Belgium as a Visiting Scientist. From 2004 to 2006, he has worked with Professor Zhi-Qiang Liu as a Postdoctoral Researcher in the Center for Media Technology (RCMT), School of Creative Media, City University of Hong Kong, Hong Kong SAR. From 2006 to 2007, Dr. Xie has worked with Professor Helen Meng as a Postdoctoral Fellow and a Project Lead in the Human-Computer Communications Laboratory (HCCL), Department of Systems Engineering & Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR. He was also a visiting professor in the University of East Anglia (UEA), United Kingdom in 2011.

Dr. Xie's general research interests include audio, speech and language processing, multimedia information processing, human-computer interaction and machine learning. Current research topics include robust speech recognition, speech synthesis, speaker recognition, spoken term detection and low-resource speech processing. He has published over 140 papers in refereed journals and major conferences, including IEEE Transactions on Multimedia, IEEE/ACM Transactions on Audio, Speech and Language Processing, Pattern Recognition, ICASSP, Interspeech, ACL and ACMMM. Dr Xie has served as program/organizing chairs and program committee members of various international conferences. He served as the Publication Chair of Interspeech2014, Program Chair of ISCSLP2016, NCMMSC2011 and ICOT2014. He served as an associate editor of IEEE/ACM Transactions on Audio, Speech and Language Processing. Dr. Xie is the principal investigator (PI) of many research projects, funded by National Natural Science Foundation of China (NSFC), Ministry of Education, and Research Grant Council (RCG) of Hong Kong SAR. He is a Senior Member of IEEE, a member of ISCA, a member of ACM, a member of APSIPA, a member of SIG-CSLP and a senior member of China Computer Federation (CCF). He is a Board-of-Governor of the Chinese Information Processing Society of China (CIPSC), the vice director of speech information processing technical committee of CIPSC, a board member of the APSIPA Speech, Language and Audio (SLA) technical committee, a board member of the multimedia technical committee of CCF, a board member of the multimedia technical committee of China Society of Image and Graphics (CSIG). a standing committee member of NCMMSC. He serves as the workgroup chair of the ISCA special interest group of Chinese spoken language processing (SIG-CSLP). He has enrolled in the Program for New Century Excellent Talents in University in 2008, supported by the Ministry of Education (MOE) of China. Dr. Xie works closely with industrial collaborators, including Baidu, Sogou, Microsoft, Huawei, Xiaomi, Alibaba, Tencent, Samsung, JD.com, Mobvoi and Unisound.

Research Interests

Audio, Speech and Language Processing, including but not limited to: Robust Speech Recognition, Speech Synthesis, Speaker Recognition, Spoken Term Detection, Low-resource Speech Processing
Multimedia/Multimodal Information Processing
Machine Learning
Human Computer Interaction

Recent Selected Publications

Sining Sun, Yangyang Shi, Ching-Feng Yeh, Suliang Bu, Mei-Yuh Hwang, Lei Xie, "Multiple Beamformers with ROVER for the CHiME-5 Challenge", The 5th CHiME Speech Separation and Recognition Challenge (CHiME-5), September 7, 2018, Hyderabad, India PDF

Jingyong Hou, Wenping Hu, Frank K. Soong, Lei Xie, "A Refined Query-by-Example Approach to Spoken Term Detection on ESL Learners' Speech", International Symposium on Chinese Spoken Language Processing (ISCSLP2018), November 26-29, 2018, Taipei, Taiwan PDF

Xiaochun An, Yuchao Zhang, Bing Liu, Liumeng Xue, Lei Xie, "A Kullback-Leibler Divergence Based Recurrent Mixture Density Network for Acoustic Modeling in Emotional Statistical Parametric Speech Synthesis", ACM Multimedia ASMMC Workshop, 26 October 2018, Seoul, Korea PDF

Liumeng Xue, Xiaolian Zhu, Xiaochun An, Lei Xie, "A Comparison of Expressive Speech Synthesis Approaches based on Neural Network", ACM Multimedia ASMMC Workshop, 26 October 2018, Seoul, Korea PDF

Sining Sun, Ching-Feng Yeh, Mari Ostendorf, Mei-Yuh Hwang, Lei Xie, "Training Augmentation with Adversarial Examples for Robust Speech Recognition", Interspeech2018, September 2-6, 2018, Hyderabad, India PDF

Changhao Shan, Junbo Zhang, Yujun Wang, Lei Xie, "Attention-based End-to-End Models for Small-Footprint Keyword Spotting", Interspeech2018, September 2-6, 2018, Hyderabad, India PDF

Ke Wang, Junbo Zhang, Sining Sun, Yujun Wang, Fei Xiang, Lei Xie, "Investigating Generative Adversarial Networks based Speech Dereverberation for Robust Speech Recognition", Interspeech2018, September 2-6, 2018, Hyderabad, India PDF

Ke Wang, Junbo Zhang, Yujun Wang, Lei Xie, "Empirical Evaluation of Speaker Adaptation on DNN based Acoustic Model", Interspeech2018, September 2-6, 2018, Hyderabad, India PDF

Yougen Yuan, Cheung-Chi Leung, Lei Xie1, Hongjie Chen, Bin Ma, Haizhou Li, "Learning Acoustic Word Embeddings with Temporal Context for Query-by-Example Speech Search", Interspeech2018, September 2-6, 2018, Hyderabad, India PDF

Pengcheng Guo, Haihua Xu, Lei Xie, Eng Siong Chng, "Study of Semi-supervised Approaches to Improving English-Mandarin Code-Switching Speech Recognition", Interspeech2018, September 2-6, 2018, Hyderabad, India PDF

Lei Xie, Tan Lee, Man-Wai Mak, "Guest Editorial: Advances in Deep Learning for Speech Processing", Journal of Signal Processing Systems, 2018 PDF

Sining Sun, Ching-Feng Yeh, Mei-Yuh Hwang, Mari Ostendorf, Lei Xie, "DOMAIN ADVERSARIAL TRAINING FOR ACCENTED SPEECH RECOGNITION", ICASSP2018, 15-20 April 2018, Calgary, Alberta, Canada PDF

Qing Wang, Wei Rao, Sining Sun, Lei Xie, Eng Siong Chng, Haizhou Li, "UNSUPERVISED DOMAIN ADAPTATION VIA DOMAIN ADVERSARIAL TRAINING FOR SPEAKER RECOGNITION", ICASSP2018, 15-20 April 2018, Calgary, Alberta, Canada PDF

Changhao Shan, Junbo Zhang, Yujun Wang, Lei Xie, "ATTENTION-BASED END-TO-END SPEECH RECOGNITION ON VOICE SEARCH", ICASSP2018, 15-20 April 2018, Calgary, Alberta, Canada PDF

Hongjie Chen, Cheung-Chi Leung, Lei Xie, Bin Ma, Haizhou Li, "Multi-Task Feature Learning for Low-Resource Query-by-Example Spoken Term Detection", IEEE Journal of Selected Topics in Signal Processing, 2017 PDF

Hongjie Chen, Cheung-Chi Leung, Lei Xie, Bin Ma, Haizhou Li, "MULTILINGUAL BOTTLE-NECK FEATURE LEARNING FROM UNTRANSCRIBED SPEECH", 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU2017), December 16-20, 2017, Okinawa, Japan PDF

Shan Yang, Lei Xie, Xiao Chen, Xiaoyan Lou, Xuan Zhu, Dongyan Huang, Haizhou Li, "Statistical Parametric Speech Synthesis Using Generative Adversarial Networks Under A Multi-task Learning Framework", 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU2017), December 16-20, 2017, Okinawa, Japan PDF

Yougen Yuan, Cheung-Chi Leung, Lei Xie, Hongjie Chen, Bin Ma, Haizhou Li, "EXTRACTING BOTTLENECK FEATURES AND WORD-LIKE PAIRS FROM UNTRANSCRIBED SPEECH FOR FEATURE REPRESENTATION ", 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU2017), December 16-20, 2017, Okinawa, Japan PDF

Jia Yu, Lei Xie, Xiong Xiao, Eng Siong Chng, "An End-to-End Neural Network Approach to Story Segmentation", 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2017), December 12-15, 2017, Kuala Lumpur, Malaysia PDF

Jia Yu, Lei Xie, Xiong Xiao, Eng Siong Chng, "Topic Embedding of Sentences for Story Segmentation", 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2017), December 12-15, 2017, Kuala Lumpur, Malaysia PDF

Jie Yan, Lei Xie, Guangsen Wang, Zhong-Hua Fu, "A Segmental DNN/i-vector Approach for Digit-Prompted Speaker Verification", 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2017), December 12-15, 2017, Kuala Lumpur, Malaysia PDF

Chenglin Xu, Lei Xie, Xiong Xiao, "A Bidirectional LSTM Approach with Word Embeddings for Sentence Boundary Detection", Journal of Signal Processing Systems, Springer, 2017 PDF

Jia Yu, Lei Xie, Xiong Xiao, Eng Siong Chng, "Learning Distributed Sentence Representations for Story Segmentation", Signal Processing, 2017 PDF

Wenpeng Li, BinBin Zhang, Lei Xie, Dong Yu, "Empirical Evaluation of Parallel Training Algorithms on Acoustic Modeling", Interspeech2017, August 20-24, Stockholm, Sweden. PDF

Jie Wu, Dongyan Huang, Lei Xie and Haizhou Li, "Denoising Recurrent Neural Network for Deep Bidirectional LSTM based Voice Conversion", Interspeech2017, August 20-24, Stockholm, Sweden. PDF

Yanfeng Lu, Zhengchen Zhang, Chenyu Yang, Huaiping Ming, Xiaolian Zhu, Yuchao Zhang, Shan Yang, Dongyan Huang, Lei Xie, Minghui Dong, "The I2R-NWPU Text-to-Speech System for Blizzard Challenge 2017", Blizzard Challenge 2017 Workshop, August 2017, Stockholm, Sweden pdf

Yougen Yuan, Lei Xie, Zhong-Hua Fu, Qi Cong, "Sound image externalization for headphone based real-time 3D audio", Frontiers of Computer Science, June 2017, Volume 11, Issue 3, pp 419-428.

Lei Xie, Lijuan Wang and Shan Yang, "Visual Speech Animation", Book Chapter in Handbook of Human Motion, Springer, 2017 PDF

Yougen Yuan, Cheung-Chi Leung, Lei Xie, Hongjie Chen, Bin Ma, Haizhou Li, "Pairwise learning using multi-lingual bottleneck features for low-resource query-by-example spoken term detection",ICASSP 2017, March 5-9, 2017, New Orleans, USA. PDF

Hongjie Chen, Lei Xie, Cheung-Chi Leung, Bin Ma and Haizhou Li, "Modeling Latent Topics and Temporal Distance for Story Segmentation of Broadcast News", IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 25, no. 1, January 2017 PDF

Sining Sun, Binbin Zhang, Lei Xie and Yanning Zhang, An unsupervised deep domain adaptation approach for robust speech recognition, Neurocomputing, 2017 PDF

Jingyong Hou, Lei Xie, Zhonghua Fu, "Investigating Neural Network based Query-by-Example Keyword Spotting Approach for Personalized Wake-up Word Detection in Mandarin Chinese", the 10th International Symposium on Chinese Spoken Language Processing (ISCSLP2016), October 17-20, 2016, Tianjin, China PDF

Changhao Shan, Lei Xie, Kaisheng Yao, "A Bi-directional LSTM Approach for Polyphone Disambiguation in Mandarin Chinese", the 10th International Symposium on Chinese Spoken Language Processing (ISCSLP2016), October 17-20, 2016, Tianjin, China PDF

Kaituo Xu, Lei Xie, Kaisheng Yao, "Investigating LSTM for Punctuation Prediction", the 10th International Symposium on Chinese Spoken Language Processing (ISCSLP2016), October 17-20, 2016, Tianjin, China PDF

Zhengchen Zhang, Mei Li, Yuchao Zhang, Weini Zhang, Yang Liu, Shan Yang, Yanfeng Lu,Van Tung Pham, Lei Xie, Minghui Dong, "The I2R-NWPU-NTU Text-to-Speech System at Blizzard Challenge 2016", Blizzard Challenge 2016 Workshop, September 16, 2016, Apple Inc., Cupertino, CA, USA PDF

Dong-Yan Huang, Lei Xie, Yvonne Siu Wa Lee, Jie Wu, Huaiping Ming, Xiaohai Tian, Shaofei Zhang, Chuang Ding, Mei Li, Quy Hy Nguyen, Minghui Dong, Haizhou Li, "An Automatic Voice Conversion Evaluation Strategy Based on Perceptual Background Noise Distortion and Speaker Similarity", the 9th ISCA Workshop on Speech Synthesis (SSW9), September 13th -15th, 2016, Sunnyvale, CA, USA PDF

Mei Li, Zhizheng Wu, Lei Xie, "On the impact of phoneme alignment in DNN-based speech synthesis", Mei Li, Zhizheng Wu, Lei Xie, the 9th ISCA Workshop on Speech Synthesis (SSW9), September 13th -15th, 2016, Sunnyvale, CA, USA PDF

Jie Wu, Zhizheng Wu, Lei Xie, "On the Use of I-vectors and Average Voice Model for Voice Conversion without Parallel Data", Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2016), December 13-16, 2016, Jeju, Korea PDF

Shan Yang, Zhizheng Wu, Lei Xie, "On the training of DNN-based average voice model for speech synthesis", Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2016), December 13-16, 2016, Jeju, Korea PDF

Zhen Wei, Zhizheng Wu, Lei Xie, "Predicting Articulatory Movement from Text Using Deep Architecture with Stacked Bottleneck Features", Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC 2016), December 13-16, 2016, Jeju, Korea PDF

Xiong Xiao, Chenglin Xu, Zhaofeng Zhang, Shengkui Zhao, Sining Sun, Shinji Watanabe, Longbiao Wang, Lei Xie, Douglas L. Jones, Eng Siong Chng, Haizhou Li, Investigation of Neural Networks Based Beamforming Approaches for Speech Recognition: The NTU Systems for CHiME-4 Evaluation, the 4th International Workshop on Speech Processing in Everyday Environments (CHiME), San Francisco, September 13, 2016 PDF

Hongjie Chen, Cheung-Chi Leung, Lei Xie, Bin Ma and Haizhou Li, "Unsupervised Bottleneck Features for Low-Resource Query-by-Example Spoken Term Detection", Interspeech2016, September 8-12, 2016, San Francisco, USA PDF

Yougen Yuan, Cheung-Chi Leung, Lei Xie, Bin Ma and Haizhou Li, "Learning Neural Network Representations using Cross-lingual Bottleneck Features with Word-pair Information", Interspeech2016, September 8-12, 2016, San Francisco, USA PDF

Jia Yu, Xiong Xiao, Lei Xie, Eng Siong Chng and Haizhou Li, "A DNN-HMM Approach to Story Segmentation", Interspeech2016, September 8-12, 2016, San Francisco, USA PDF

Huaiping Ming, Dongyan Huang, Lei Xie, Jie Wu, Minghui Dong and Haizhou Li, "Deep Bidirectional LSTM Modeling of Timbre and Prosody for Emotional Voice Conversion", Interspeech2016, September 8-12, 2016, San Francisco, USA PDF

Cheung-Chi Leung, Lei Wang, Haihua Xu, Jingyong Hou, Van Tung Pham, Hang Lv, Lei Xie, Xiong Xiao, Chongjia Ni, Bin Ma, Eng Siong Chng, Haizhou Li,"Toward High-Performance Language-Independent Query-by-Example Spoken Term Detection for MediaEval 2015: Post-Evaluation Analysis", Interspeech2016, September 8-12, 2016, San Francisco, USA PDF

Bihong Zhang, Lei Xie, Yougen Yuan, Huaiping Ming, Dongyan Huang and Mingli Song, "Deep neural network derived bottleneck features for accurate audio classification", ICME2016, S July 11-15, 2016, Seattle, USA PDF

Huaiping Ming, Dongyan Huang, Lei Xie, Shaofei Zhang, Minghui Dong and Haizhou Li, "Exemplar-based Sparse Representation of Timbre and Prosody for Voice Conversion", ICASSP2016, March 20-25, 2016, Shanghai, China PDF

Haihua Xu, Jingyong Hou, Xiong Xiao, Van Tung Pham, Cheung-Chi Leung, Lei Wang, Van Hai Do, Hang Lv, Lei Xie, Bin Ma, Eng Siong Chng, Haizhou Li, "Approximate Search of Audio Queries using DTW with Phone Time Boundary and Data Augmentation", ICASSP2016, March 20-25, 2016, Shanghai, China PDF

Chuang Ding, Lei Xie, Jie Yan, Weini Zhang and Yang Liu, "Automatic Prosody Prediction for Chinese Speech Synthesis using BLSTM-RNN and Embedding Features",2016 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU2016), Dec 13-17, 2016, Scottsdale, Arizona PDF

Jingyong Hou, Van Tung Pham, Cheung-Chi Leung, Lei Wang, Haihua Xu, Hang Lv, Lei Xie, Zhonghua Fu, Chongjia Ni, Xiong Xiao, Hongjie Chen, Shaofei Zhang, Sining Sun, Yougen Yuan, Pengcheng Li, Tin Lay Nwe, Sunil Sivadas, Bin Ma, Eng Siong Chng, Haizhou Li,"The NNI Query-by-Example System for MediaEval 2016", MediaEval 2016 Workshop, Wurzen, Germany, Sept 14-15, 2016 PDF (Best performing system in the MediaEval2016 QUESST Evaluation)

Xiangzeng Zhou, Lei Xie, Peng Zhang and Yanning Zhang, "Online Object Tracking based on CNN with Metropolis-Hasting Re-sampling", ACM Multimedia 2016, Brisbane, Australia, Oct 26-30, 2016 PDF

Bo Fan, Lei Xie, Shan Yang, Lijuan Wang and Frank K. Soong, "A Deep Bidirectional LSTM Approach for Video-Realistic Talking Head", Multimedia Tools and Applications, Springer, 2016PDF

Bo Fan, Sui Wa Lee, Xiaohai Tian, Lei Xie and Minghua Dong, "A Waveform Representation Framework for High-quality Statistical Parametric Speech Synthesis", APSIPA ASC 2016, Hong Kong, China, Dec 16-19, 2016 PDF

Jia Yu, Lei Xie, Xiao Xiong, Eng Siong Chng, Haizhou Li, "A Density Peak Clustering Approach to Unsupervised Acoustic Subword Units Discovery", APSIPA ASC 2016, Hong Kong, China, Dec 16-19, 2016 PDF

Shaofei Zhang, Dongyan Huang, Lei Xie, Eng Siong Chng, Haizhou Li and Minghui Dong, "Non-negative Matrix Factorization using Stable Alternating Direction Method of Multipliers for Source Separation", APSIPA ASC 2016, Hong Kong, China, Dec 16-19, 2016 PDF

Hongjie Chen, Cheung-Chi Leung, Lei Xie, Bin Ma and Haizhou Li, Parallel Inference of Dirichlet Process Gaussian Mixture Models for Unsupervised Acoustic Modeling: A Feasibility Study, Interspeech2016, September 6-10, Dresden, Germany PDF (Interspeech2016 Zerospeech Challenge Best Paper Award)

Huaiping Ming, Dongyan Huang, Lei Xie, Haizhou Li and Minghui Dong, An Alternating Optimization Approach for Phase Retrieval Interspeech2016, September 6-10, Dresden, Germany PDF

Pengcheng Zhu, Lei Xie, Yunlin Chen, Articulatory Movement Prediction Using Deep Bidirectional Long Short-Term Memory Based Recurrent Neural Networks andWord/Phone Embeddings,Interspeech2016, September 6-10, Dresden, Germany PDF

Shaofei Zhang, Dongyan Huang, Lei Xie, Eng Siong Chng, Haizhou Li, Minghui Dong, Regularized Non-negative Matrix Factorization Using Alternating Direction Method of Multipliers and Its Application to Source SeparationInterspeech2016, September 6-10, Dresden, Germany PDF

Xiangzeng Zhou, Lei Xie, Qiang Huang, Stephen Cox and Yanning Zhang, Tennis Ball Tracking using a Two-Layered Data Association Approach, IEEE Transactions on Multimedia, 2014 PDF

Bo Fan, Lijuan Wang, Frank K. Soong and Lei Xie, Photo-real Talking Head with Deep Bidirectional LSTM, ICASSP2016, 19-24 April 2016, Brisbane, Australia PDF

Haihua Xu, Peng Yang, Xiong Xiao, Lei Xie, Cheung-Chi Leung, Hongjie Chen, Jia Yu, Hang Lv, Lei Wang, Su Jun Leow, Bin Ma, Eng Siong Chng, Haizhou Li, Language Independent Query-by-Example Spoken Term Detection using N-Best Phone Sequences and Partial Matching, ICASSP2016, 19-24 April 2016, Brisbane, Australia PDF

Peng Yang, Haihua Xu, Xiong Xiao, Lei Xie, Cheung-Chi Leung, Hongjie Chen, Jia Yu, Hang Lv, Lei Wang, Su Jun Leow, Bin Ma, Eng Siong Chng, Haizhou Li, "The NNI Query-by-Example System for MediaEval 2014", MediaEval 2014 Workshop, Barcelona, Spain, Oct 16-17, 2014 PDF

Guangpu Huang, Chenglin Xu, Xiong Xiao, Lei Xie, Eng Siong Chng, Haizhou Li, " Multi-View Features in a DNN-CRF Model for Improved Sentence Unit Detection on English Broadcast News", APSIPA ASC 2014, Siem Reap, Cambodia, December 9-12, 2014

Chuang Ding, Pengcheng Zhu, Lei Xie, Dongmei Jiang and Zhonghua Fu, "Speech-Driven Head Motion Synthesis Using Neural Networks," Interspeech, Singapore, 14-18, September 2014 PDF

Chenglin Xu, Lei Xie, Guangpu Huang, Xiong Xiao, Eng Siong Chng and Haizhou Li, "A Deep Neural Network Approach for Sentence Boundary Detection in Broadcast News," Interspeech, Singapore, 14-18, September 2014 PDF

Peng Yang, Cheung-Chi Leung, Lei Xie, Bin Ma and Haizhou Li, "Intrinsic Spectral Analysis Based on Temporal Context Features for Query by Example Spoken Term Detection," Interspeech, Singapore, 14-18, September 2014 (Best Student Paper Finalist) PDF

Zhong-hua Fu, Lei Xie, "Stereo Acoustic Echo Suppression Using Widely Linear Filtering in the Frequency Domain," Interspeech, Singapore, 14-18, September 2014

Shaofei Zhang, Lei Xie, Zhong-hua Fu, "A Hybrid Virtual Bass System with Improved Phase Vocoder and High Efficiency,” ISCSLP, Singapore, 12-14, September 2014

Zhong-hua Fu, Lei Xie, "Experimental Study on Dereverberation and Noise Reduction for Distant Speech Recognition,” ISCSLP, Singapore, 12-14, September 2014

Hongjie Chen, Lei Xie, Wei Feng, Lilei Zheng and Yanning Zhang, "Topic Segmentation on Spoken Documents Using Self-Validated Acoustic Cuts,” Soft Computing, Springer, accepted, June 2014

Xiangzeng Zhou, Lei Xie, Peng Zhang, Yanning Zhang, "An Ensemble of Deep Neural Networks for Object Tracking", ICIP2014, October 27-30, 2014, Paris, France PDF

Chuang Ding, Lei Xie, Pengcheng Zhu, " "Head Motion Synthesis From Speech Using Deep Neural Networks", Multimedia Tools and Applications, Springer, accepted, 2014

Chao Yang, Lei Xie and Xiangzeng Zhou, "Unsupervised Broadcast News Story Segmentation Using Distance Dependent Chinese Restaurant Processes", ICASSP2014, May 4-9, 2014, Florence, Italy PDF

Huaiping Ming, Dongyan Huang, Lei Xie and Haizhou Li, "Learning Optimal Features for Music Transcription", the 2nd IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP2014), July 9-13, 2014, Xi'an, China

Chenglin Xu, Lei Xie and Zhonghua Fu, "Sentence Boundary Detection in Chinese Broadcast News using Conditional Random Fields and Prosodic Features", the 2nd IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP2014), July 9-13, 2014, Xi'an, China

Huaiping Ming, Lei Xie and Haizhou LI, "Filter Bank Design for Automatic Music Transcription", the 2013 Young Engineers and Scientists Conference on Multimedia, Communication and Mobile Application Technologies (YES2013), Nov. 8, 2013, Singapore

Xiaoming Lu, Lei Xie, Cheung-Chi Leung, Bin Ma and Haizhou Li, "Broadcast News Story Segmentation Using Manifold Learning on Latent Topic Distributions", ACL2013, 4-9 August, 2013, Sofia, Bulgaria. PDF

Jianwei Niu, Lei Xie, Lei Jia and Na Hu, "Context-Dependent Deep Neural Networks for Commercial Mandarin Speech Recognition Applications", APSIPA Annual Summit and Conference (APSIPA ASC 2013), Kaohsiung, Taiwan, Oct. 29 - Nov. 1, 2013. PDF

Haoran Liang, Mingli Song, Lei Xie and Ronghua Liang, "Personalized 3-D Facial Expression Synthesis based on Landmark Constraint", APSIPA Annual Summit and Conference (APSIPA ASC 2013), Kaohsiung, Taiwan, Oct. 29 - Nov. 1, 2013.

Ling Tang, Zhong-Hua Fu and Lei Xie, "Numerical Calculation of the Head-Related Transfer Functions with Chinese Dummy Head", APSIPA Annual Summit and Conference (APSIPA ASC 2013), Kaohsiung, Taiwan, Oct. 29 - Nov. 1, 2013.

Lei Xie, Zhigang Deng and Stephen Cox, "Multimodal joint information processing in human machine interaction: recent advances", Multimedia Tools and Applications, Guest Editorial, Springer, November, 2013.

Lei Xie, Naicai Sun and Bo Fan, "A Statistical Parametric Approach to Video-Realistic Text-driven Talking Avatar", Multimedia Tools and Applications, Springer, August 2013.

Peng Yang, Lei Xie, Qiao Luan and Wei Feng, "A Tighter Lower Bound Estimate for Dynamic Time Warping", ICASSP2013, May 26-31, 2013, Vancouver, Canada PDF

Xiangzeng Zhou, Qiang Huang, Lei Xie and Stephen Cox, "A Two Layered Data Association Approach for Ball Tracking", ICASSP2013, May 26-31, 2013, Vancouver, Canada PDF

Xiaoming Lu, Cheung-Chi Leung, Lei Xie, Bin Ma, Haizhou Li, "Broadcast News Story Segmentation Using Latent Topics on Data Manifold", ICASSP2013, May 26-31, 2013, Vancouver, Canada PDF

Xuecheng Nie, Wei Feng, Liang Wan, Lei Xie, "Measuring Similarity by Contextual Word Connections in Chinese News Story Segmentation", ICASSP2013, May 26-31, 2013, Vancouver, Canada

Bingfeng Li, Lei Xie, Pengcheng Zhu and Fan Bo, "Head Motion Generation for Speech-driven Talking Avatar", NCMMSC2013, Journal of Tsinghua University (Sci and Tech), No.6, 2013 PDF

Peng Yang, Lei Xie and Hongjie Chen, "Speech Pattern Discovery using Segmental Dynamic Time Warping and Posteriorgram Features", NCMMSC2013, Journal of Tsinghua University (Sci and Tech), No.6, 2013 PDF

Lei Xie, Lilei Zheng, Zihan Liu and Yanning Zhang, "Laplacian Eigenmaps for Automatic Story Segmentation of Broadcast News," IEEE Transactions on Audio, Speech and Language Processing, vol. 20, no. 1, pp 264-277, January 2012. PDF Bib

Lei Xie, Yinqing Xu, Lilei Zheng, Qiang Huang and Bingfeng Li, "Speech Pattern Discovery using Audio-Visual Fusion and Canonical Correlation Analysis", Interspeech, Portland, Oregon, USA, September 9-13, 2012. PDF Bib Poster

Yali Zhao, Lei Xie and Zhonghua Fu, "A Two Stage Mask Estimation Approach to Robust Speaker Verification", Interspeech, Portland, Oregon, USA, September 9-13, 2012. PDF Bib Poster

Wei Feng, Xuecheng Nie, Liang Wan, Lei Xie and Jianmin Jiang, "Lexical Story Co-Segmentation of Chinese Broadcast News", Interspeech, Portland, Oregon, USA, September 9-13, 2012. PDF Bib

Lei Xie, Chenglin Xu and Xiaoxuan Wang, "Prosody-based Sentence Boundary Detection in Chinese Broadcast News", The 8th International Symposium on Chinese Spoken Language Processing (ISCSLP2012) , Hong Kong, China, December 5-8, 2012 PDF Bib

Qiang Huang, Stephen Cox, Xiangzeng Zhou and Lei Xie, "Detection of Ball Hits in a Tennis Game Using Audio and Visual Information", APSIPA Annual Summit and Conference (APSIPA ASC 2012), Hollywood, California, USA, Dec 3-6, 2012

Yang Liang, Mingli Song, Lei Xie, Jiajun Bu and Chun Chen,"Face Sketch-to-Photo Synthesis from Simple Line Drawing", APSIPA Annual Summit and Conference (APSIPA ASC 2012), Hollywood, California, USA, Dec 3-6, 2012

Lilei Zheng, Cheung-Chi Leung, Lei Xie, Bin Ma, Haizhou Li, "Acoustic Texttiling For Story Segmentation Of Spoken Documents", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2012), March 25 - 30, Kyoto, Japan, 2012. PDF Bib Poster

Yali Zhao, Zhong-Hua Fu, Lei Xie, Jian Zhang, Yanning Zhang, "Dual-microphone based binary mask estimation for robust speaker verification", International Conference on Audio, Language and Image Processing (ICALIP), Shanghai, China, July 16 -18, 2012.

Dan Li, Zhong-Hua Fu and Lei Xie, "Comprehensive Comparison of the Least Mean Square Algorithm and the Fast Deconvolution Algorithm for Crosstalk Cancellation", International Conference on Audio, Language and Image Processing (ICALIP), Shanghai, China, July 16 -18, 2012.

Lei Xie, Yulian Yang and Zhi-Qiang Liu, "On the Effectiveness of Subwords for Lexical Cohesion Based Story Segmentation of Chinese Broadcast News", Information Sciences, 181(13):2873–2891, Elsevier, 2011. PDF Bib

Mimi Lu, Cheung-Chi Leung, Lei Xie, Bin Ma, Haizhou Li, "Probabilistic Latent Semantic Analysis for Broadcast News Story Segmentation", Interspeech2011, Florence, Italy, August, 2011. (Interspeech Grant) PDF Bib Slides

Xiaoxuan Wang, Lei Xie, Bin Ma, Eng Siong Chng and Haizhou Li, "Broadcast News Story Segmentation Using Conditional Random Fields and Multi-modal Features", IEICE Transactions on Information and Systems, Vol. E95-D, No. 5, pp. 1206-1215, May 2012. PDF Bib

Mimi Lu, Lilei Zheng, Cheung-Chi Leung, Lei Xie, Bin Ma and Haizhou Li, "Broadcast News Story Segmentation Using Probabilistic Latent Semantic Analysis and Laplacian Eigenmaps", APSIPA Annual Summit and Conference (APSIPA ASC 2011), Xi'an, China, 2011. PDF Bib

Xiaoyu Chen, Zhonghua Fu and Lei Xie, "Multiple Sparse Sources Separation Based on Multichannel Frequency Domain Adaptive Filtering", APSIPA Annual Summit and Conference (APSIPA ASC 2011), Xi'an, China, 2011

Jian Zhang, Zhonghua Fu and Lei Xie, "A Block-Based Blind Source Separation Approach with Equilateral Triangular Microphone Array", APSIPA Annual Summit and Conference (APSIPA ASC 2011), Xi'an, China, 2011

Lei Xie, Zhong-hua Fu, Wei Feng and Yong Luo,"Pitch-Density-based Features and an SVM Binary Tree Approach for Multi-Class Audio Classification in Broadcast News", ACM/Springer Multimedia Systems Journal, 17(2):101-112 , 2011. PDF Bib

LI Bingfeng, XIE Lei, ZHOU Xiangzeng, FU Zhonghua and ZHANG Yanning, "Real-time speech driven talking avatar", Journal of Tsinghua University, 2011, 51(9):1180-1186. (In Chinese, selected paper from NCMMSC2011, Best Student Paper Nomination Award) PDF Bib

ZHANG Jian, FU Zhonghua, XIE Lei and ZHAO Yali, "Semi-blind dual-microphone noise reduction with known target localization", Journal of Tsinghua University. 2011, 51(9):1215-1219. (In Chinese, selected paper from NCMMSC2011)

ZHENG Li-lei, XIE Lei, LU Mi-mi, WANG Xiao-xuan, YANG Yu-lian and ZHANG Yan-ning, "An Automatic Caption Generator for Mandarin Broadcast News", Chinese Journal of Electronics, 39(3A): 69-74, 2011. PDF Bib

Mimi Lu, Lei Xie, Zhonghua Fu, Dongmei-Jiang, "Multi-Modal Feature Integration for Story Boundary Detection in Broadcast News", International Symposium on Chinese Spoken Language Processing (ISCSLP2010), Tainan, Taiwan, 2010. PDF Bib

Xiaoxuan Wang, Lei Xie, Bin Ma, Eng Siong Chng, Haizhou Li, "Modeling Broadcast News Prosody Using Conditional Random Fields for Story Segmentation", APSIPA Annual Summit and Conference (APSIPA ASC 2010), Biopolis, Singapore, December 14-17, 2010. PDF Bib

Zihan Liu, Lei Xie, Wei Feng, "Maximum Lexical Cohesion for Fine-Grained News Story Segmentation," Interspeech2010, Makuhari, Japan, 26-30 September, 2010. (Interspeech Best Student Paper Award Finalist) PDF Bib

Xiaoxuan Wang, Lei Xie, Bin Ma, Eng Siong Chng, Haizhou Li, "Phoneme Lattice based TextTiling towards Multilingual Story Segmentation," Interspeech2010, Makuhari, Japan, 26-30 September, 2010. PDF Bib

Lei Xie, Yulian Yang, Zhi-Qiang Liu, Wei Feng and Zihan Liu, "Integrating Acoustic and Lexical Features In Topic Segmentation of Chinese Broadcast News Using Maximum Entropy Approach," International Conference on Audio, Language and Image Processing (ICALIP), Shanghai, China, 23-25 November 2010.

Zihan Liu, Lei Xie and Lilei Zheng, "Laplacian Eigenmaps for Automatic News Story Segmentation", International Conference on Audio, Language and Image Processing (ICALIP), Shanghai, China, 23-25 November 2010.

Lei Xie et al., "Speech and Auditory Interfaces for Ubiquitous, Immersive and Personalized Applications," Demo for The 7th International Conference on Ubiquitous Intelligence and Computing(UIC), October 26-29, 2010, Xi'an, China

Xiaohai Tian, Zhonghua Fu and Lei Xie, "An Experimental Comparison on KEMAR and BHead210 Dummy Heads for HRTF-based Virtual Auditory on Chinese Subjects," The Third IET International Conference on Wireless, Mobile & Multimedia Networks (ICWMMN2010), 26 - 29, September 2010, Beijing, China.

Yaodong Ni, Lei Xie, and Zhi-Qiang Liu, " Minimizing the Expected Complete Influence Time of a Social Network," Information Sciences, 180(13): 2514-2527, 2010.

Wei Feng, Lei Xie and Zhi-Qiang Liu, "Multicue Graph Mincut for Image Segmentation", Ninth Asian Conference on Computer Vision (ACCV2009), LNCS 5995, pp. 707-717, Springer, 2010.

Jin Zhang, Lei Xie, Wei Feng and Yanning Zhang, "A Subword Normalized Cut Approach to Automatic Story Segmentation of Chinese Broadcast News", Asia Information Retrieval Symposium (AIRS2009), LNCS 5839, Springer, pp136-148, 2009.

Wei Feng, Lei Xie, Jia Zeng and Zhi-Qiang Liu, "Audio-Visual Human Recognition Using Semi-Supervised Spectral Learning and Hidden Markov Models," Journal of Visual languages and Computing , invited paper, 20(3):188-195, 2009.

Jia Zeng, Wei Feng, Lei Xie and Zhi-Qiang Liu, "Cascade Markov random fields for stroke extraction of Chinese characters," Information Sciences, 180(2):301-311, 2009.

Lilei Zheng, Lei Xie, Xiaoxuan Wang, Mimi Lu, Yulian Yang and Yanning Zhang, "An Antomatic Caption Generator for Mandarin Broadcast News," 5th Joint Conference on Harmonious Human Machine Environment (HHME2009), Xi'an, China, Oct 28-30, 2009 (Best Paper Award)

Mimi Lu, Lei Xie, Lilei Zheng, Yulian Yang, Yanning Zhang, "Anchor Labeling System for Broadcast News using Alize toolkit", 5th Joint Conference on Harmonious Human Machine Environment (HHME2009), Xi'an, China, Oct 28-30, 2009

Zhonghua Fu, Jhing-Fa Wang and Lei Xie, "Noise Robust Features for Speech/Music Discrimination in Real-time Telecommunication", IEEE International Conference on Multimedia and Expo (ICME 2009), pp 574-577, New York, USA.

Lei Xie, "Discovering salient prosodic cues and their interactions for automatic story segmentation in Mandarin broadcast news", ACM/Springer Multimedia Systems Journal, 14(4):237-253, 2008.

Jia Zeng, Lei Xie and Zhi-Qiang Liu, "Type-2 Fuzzy Gaussian Mixture Models" Pattern Recognition, 41, 2008, pp 3636-3643.

Lei Xie and Guangsen Wang, "A Two-stage Multi-feature integration approach to Unsupervised Speaker Change Detection in Real-time News Broadcasting", International Symposium on Chinese Spoken Language Processing (ISCSLP), pp. 350-353, Yunnan, China, 2008. PDF Bib

Yulian Yang and Lei Xie, "Subword Latent Semantic Analysis for TextTiling-based Automatic Story Segmentation of Chinese Broadcast News", International Symposium on Chinese Spoken Language Processing (ISCSLP), pp. 358-361, Yunnan, China, 2008. (Microsoft Student Grant. This paper is also presented in the 2008 Beijing-Hong Kong International Doctoral Forum, Beijing) PDF Bib

Lei Xie and Yulian Yang, "Subword Lexical Chaining for Automatic Story Segmentation in Chinese Broadcast News", Pacific-Rim Conference on Multimedia (PCM2008), LNCS 5353, Springer, pp248-258, 2008.

Lei Xie, Jia Zeng and Wei Feng, "Multi-Scale TextTiling for Automatic Story Segmentation in Chinese Broadcast News", Asia Information Retrieval Symposium (AIRS2008), LNCS 4993, Harbin, China, pp345-355, Springer, 2008.

Lei Xie and Zhi-Qiang Liu, "Realistic Mouth-Synching for Speech-Driven Talking Face Using Articulatory Modelling", IEEE Transactions on Multimedia, 9(3), 2007, pp500-510. PDF Bib

Lei Xie and Zhi-Qiang Liu, "A Coupled HMM Approach for Video-Realistic Speech Animation", Pattern Recognition, 40(10), 2007, pp2325-2340. PDF Bib

Lei Xie, "Dynamic Bayesian Network Inversion for Robust Speech Recognition", IEICE Transactions on Information and Systems, 2007, Vol. E90-D, No. 7, pp 156-159.

Lei Xie, Chuan Liu and Helen Meng, "Combined Use of Speaker- and Tone-Normalized Pitch Reset with Pause Duration for Automatic Story Segmentation in Mandarin Broadcast News", Human Language Technology Conference /North American chapter of the Association for Computational Linguistics Annual Meeting (HLT-NAACL), pp193-196, Rochester, NY, USA, April, 2007.

Chuan Liu, Lei Xie, Helen Meng, "Classification of Music and Speech in Mandarin News Broadcasts", 9th National Conference on Man-Machine Speech Communication (NCMMSC), Huangshan, Anhui, China, 2007.

Shing-kai Chan, Lei Xie and Helen Mei-ling Meng, "Modeling the Statistical Behavior of Lexical Chains to Capture Word Cohesiveness for Automatic Story Segmentation" Interspeech, Belgium, 2007. PDF Bib

Lei Xie, and Zhi-Qiang Liu, "An Articulatory Approach to Video-Realistic Mouth Animation", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. I, pp593-596, Toulouse, France, 2006.

Lei Xie, Helen Meng and Zhi-Qiang Liu, "A Cantonese Speech-Driven Talking Face using Translingual Audio-to-Visual Conversion", International Symposium on Chinese Spoken Language Processing (ISCSLP2006), LNAI 4274, Singapore, pp627-639, Springer, Dec, 2006.

Lei Xie and Zhi-Qiang Liu, "Multi-Stream Articulator Model with Adaptive Reliability Measure for Audio Visual Speech Recognition", Advances in Machine Learning and Cybernetics, LNAI 3930, Springer, pp99-114, April, 2006.

Lei Xie, and Zhi-Qiang Liu, "Speech Animation Using Coupled Hidden Markov Models", International Conference on Pattern Recognition (ICPR), vol. I, pp1128-1131, Hong Kong, 2006.

Lei Xie, and Zhi-Qiang Liu, "Lip Assistant: Visualize Speech for Hearing Impaired People in Multimedia Services" , International Conference on System, Man and Cybernetics (ICSMC) , pp4331-4336, Taipei, Taiwan, 2006.

......

WARNING: This page contains links to pdf files whose contents may be covered by copyright. You may browse them at your convenience in the same spirit as you may read a journal or a conference proceedings article in a public library. Retrieving, copying, or distributing these files, however, may violate international copyright protection law.

Collaborators

Haizhou Li, Department Head, Principal Scientist, Institute for Infocomm Research (I2R), A*STAR, Singapore
Helen Meng, Professor, The Chinese University of Hong Kong, Hong Kong SAR
Hichem Sahli, Professor, Vrije Universitiet Brussel (VUB), Belgium
Stephen Cox, Professor, University of East Anglia, UK
Zhi-Qiang Liu, Professor, City University of Hong Kong, Hong Kong SAR
Jhing-Fa Wang, Professor, National Cheng Kung University, Taiwan
Frank Soong, Principal Researcher, Microsoft Research Asia, China
Dong Yu, Distinguished Scientist and Vice General Manager, Tencent AI Lab, USA
Mari Ostendorf, Professor, University of Washington, USA
Daniel Povey, Associate Research Professor, Johns Hopkins University, USA
Lijuan Wang, Researcher, Microsoft Research Asia, China
Eng Siong Chng, Professor, Nanyang Technological University, Singapore
Xiong Xiao, Senior Research Scientist, Nanyang Technological University, Singapore
Bin Ma, Senior Scientist, Institute for Infocomm Research (I2R), A*STAR, Singapore
Cheung-Chi Leung, Scientist, Institute for Infocomm Research (I2R), A*STAR, Singapore
Lee Siu Wa, Scientist, Institute for Infocomm Research (I2R), A*STAR, Singapore
Dongyan Huang, Scientist, Institute for Infocomm Research (I2R), A*STAR, Singapore
Mingli Song, Associate Professor, Zhejiang University, China
Lei Jia, Baidu, China
Zhigang Deng, Professor, University of Houston, USA
Qiang Huang, University of Edinburgh, UK
Wei Feng, Professor, Tianjin University, China
Jia Zeng, Professor, Suzhou University, China
Yi Wang, Tencent Co.
Zhonghua Fu, Professor, ASLP, Northwestern Polytechnical University, China
Dongmei Jiang, Professor, ASLP, Northwestern Polytechnical University, China
Yanning Zhang, Professor, ASLP, Northwestern Polytechnical University, China