| 2023 | ICASSP | GCC-Speaker: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios. | Guanjun Li, Wei Xue, Wenju Liu, Jiangyan Yi, Jianhua Tao |
| 2020 | Interspeech | Deep Neural Network-Based Generalized Sidelobe Canceller for Robust Multi-Channel Speech Recognition. | Guanjun Li, Shan Liang, Shuai Nie, Wenju Liu, Zhanlei Yang, Longshuai Xiao |
| 2020 | Interspeech | Microphone Array Post-Filter for Target Speech Enhancement Without a Prior Information of Point Interferers. | Guanjun Li, Shan Liang, Shuai Nie, Wenju Liu, Zhanlei Yang, Longshuai Xiao |
| 2019 | CVPR | Sequence-To-Sequence Domain Adaptation Network for Robust Text Image Recognition. | Yaping Zhang, Shuai Nie, Wenju Liu, Xing Xu, Dongxiang Zhang, Heng Tao Shen |
| 2019 | ICASSP | Adaptive Dereverberation Using Multi-channel Linear Prediction with Deficient Length Filter. | Guanjun Li, Shan Liang, Shuai Nie, Wenju Liu |
| 2019 | ICASSP | Loss and Double-edge-triggered Detector for Robust Small-footprint Keyword Spotting. | Bin Liu, Shuai Nie, Yaping Zhang, Shan Liang, Zhanlei Yang, Wenju Liu |
| 2019 | Interspeech | Direction-Aware Speaker Beam for Multi-Channel Speaker Extraction. | Guanjun Li, Shan Liang, Shuai Nie, Wenju Liu, Meng Yu, Lianwu Chen, Shouye Peng, Changliang Li |
| 2019 | Interspeech | Jointly Adversarial Enhancement Training for Robust End-to-End Speech Recognition. | Bin Liu, Shuai Nie, Shan Liang, Wenju Liu, Meng Yu, Lianwu Chen, Shouye Peng, Changliang Li |
| 2018 | ICASSP | Boosting Noise Robustness of Acoustic Model via Deep Adversarial Training. | Bin Liu, Shuai Nie, Yaping Zhang, Dengfeng Ke, Shan Liang, Wenju Liu |
| 2018 | IJCNN | Text-To-Text Generative Adversarial Networks. | Changliang Li, Yixin Su, Wenju Liu |
| 2018 | IJCNN | Stochastic Multiple Choice Learning for Acoustic Modeling. | Bin Liu, Shuai Nie, Shan Liang, Zhanlei Yang, Wenju Liu |
| 2018 | Interspeech | Deep Noise Tracking Network: A Hybrid Signal Processing/Deep Learning Approach to Speech Enhancement. | Shuai Nie, Shan Liang, Bin Liu, Yaping Zhang, Wenju Liu, Jianhua Tao |
| 2017 | ICDAR | Robust Math Formula Recognition in Degraded Chinese Document Images. | Ning Liu, Dongxiang Zhang, Xing Xu, Long Guo, Lijiang Chen, Wenju Liu, Dengfeng Ke |
| 2017 | ICDAR | An Iterative Refinement Framework for Image Document Binarization with Bhattacharyya Similarity Measure. | Ning Liu, Dongxiang Zhang, Xing Xu, Wenju Liu, Dengfeng Ke, Long Guo, Shengkun Shi, Hui Liu, Lijiang Chen |
| 2017 | Interspeech | Multilingual i-Vector Based Statistical Modeling for Music Genre Classification. | Jia Dai, Wei Xue, Wenju Liu |
| 2016 | ICASSP | Exploiting spectro-temporal structures using NMF for DNN-based supervised speech separation. | Shuai Nie, Shan Liang, Hao Li, Xueliang Zhang, Zhanlei Yang, Wenju Liu, Like Dong |
| 2016 | Interspeech | Improving Large Vocabulary Accented Mandarin Speech Recognition with Attribute-Based I-Vectors. | Hao Zheng, Shanshan Zhang, Liwei Qiao, Jianping Li, Wenju Liu |
| 2015 | ICASSP | Cross-domain cooperative deep stacking network for speech separation. | Wei Jiang, Shan Liang, Like Dong, Hong Yang, Wenju Liu, Yunji Wang |
| 2015 | ICASSP | A pairwise algorithm for pitch estimation and speech separation using deep stacking network. | Hui Zhang, Xueliang Zhang, Shuai Nie, Guanglai Gao, Wenju Liu |
| 2015 | IJCNN | Multiscale collaborative speech denoising based on deep stacking network. | Wei Jiang, Hao Zheng, Shuai Nie, Wenju Liu |
| 2015 | IJCNN | Integration of articulatory knowledge and voicing features based on DNN/HMM for Mandarin speech recognition. | Ying-Wei Tan, Wenju Liu, Wei Jiang, Hao Zheng |
| 2015 | IJCNN | Improving deep neural networks using softplus units. | Hao Zheng, Zhanlei Yang, Wenju Liu, Jizhong Liang, Yanpeng Li |
| 2015 | Interspeech | Improving deep neural networks based multi-accent Mandarin speech recognition using i-vectors and accent-specific top layer. | Mingming Chen, Zhanlei Yang, Jizhong Liang, Yanpeng Li, Wenju Liu |
| 2015 | Interspeech | "multilingual" deep neural network for music genre classification. | Jia Dai, Wenju Liu, Chongjia Ni, Like Dong, Hong Yang |
| 2015 | Interspeech | Two-stage multi-target joint learning for monaural speech separation. | Shuai Nie, Shan Liang, Wei Xue, Xueliang Zhang, Wenju Liu, Like Dong, Hong Yang |
| 2015 | Interspeech | Joint optimization of recurrent networks exploiting source auto-regression for source separation. | Shuai Nie, Wei Xue, Shan Liang, Xueliang Zhang, Wenju Liu, Liwei Qiao, Jianping Li |
| 2015 | Interspeech | Attribute knowledge integration for speech recognition based on multi-task learning neural networks. | Hao Zheng, Zhanlei Yang, Liwei Qiao, Jianping Li, Wenju Liu |
| 2015 | Interspeech | Exploring robustness of DNN/RNN for extracting speaker baum-welch statistics in mismatched conditions. | Hao Zheng, Shanshan Zhang, Wenju Liu |
| 2014 | ICASSP | Deep stacking networks with time series for speech separation. | Shuai Nie, Hui Zhang, Xueliang Zhang, Wenju Liu |
| 2014 | ICASSP | DOA estimation of speech source in noisy environments with weighted spatial bispectrum correlation matrix. | Wei Xue, Shan Liang, Wenju Liu |
| 2014 | IJCNN | Deep neural networks for Mandarin tone recognition. | Mingming Chen, Zhanlei Yang, Wenju Liu |
| 2014 | IJCNN | Hybrid SVM/HMM architectures for statistical model-based voice activity detection. | Ying-Wei Tan, Wenju Liu, Wei Jiang, Hao Zheng |
| 2014 | Interspeech | Improving native accent identification using deep neural networks. | Mingming Chen, Zhanlei Yang, Hao Zheng, Wenju Liu |
| 2014 | Interspeech | Weighted spatial bispectrum correlation matrix for DOA estimation in the presence of interferences. | Wei Xue, Shan Liang, Wenju Liu |
| 2013 | Interspeech | Interference robust DOA estimation of human speech by exploiting historical information and temporal correlation. | Wei Xue, Shan Liang, Wenju Liu |
| 2012 | ICASSP | Improved tone modeling by exploiting articulatory features for mandarin speech recognition. | Hao Chao, Zhanlei Yang, Wenju Liu |
| 2012 | Interspeech | Combining frame and segment based models for environmental sound classification. | Pengfei Hu, Wenju Liu, Wei Jiang |
| 2012 | Interspeech | A new noise-tracking algorithm for generalizing binary time-frequency (T-F) masking to ratio masking. | Shan Liang, Wei Jiang, Wenju Liu |
| 2012 | Interspeech | Direction of Arrival Estimation Based on Subband Weighting for Noisy Conditions. | Wei Xue, Wenju Liu |
| 2011 | ICASSP | A novel multi-band spectral subtraction method based on phase modification and magnitude compensation. | Chao Li, Wenju Liu |
| 2011 | ICICS | A Unified Security Framework for Multi-domain Wireless Mesh Networks. | Ze Wang, Maode Ma, Wenju Liu, Xixi Wei |
| 2011 | IJCNN | Prosody dependent Mandarin speech recognition. | Chong-Jia Ni, Wenju Liu, Bo Xu |
| 2011 | Interspeech | A Noise Estimation Method Based on Speech Presence Probability and Spectral Sparseness. | Chao Li, Wenju Liu |
| 2011 | Interspeech | Improved a posteriori Speech Presence Probability Estimation Based on Cepstro-Temporal Smoothing and Time-Frequency Correlation. | Chao Li, Wenju Liu |
| 2011 | Interspeech | Automatic Prosodic Events Detection by Using Syllable-Based Acoustic, Lexical and Syntactic Features. | Chong-Jia Ni, Wenju Liu, Bo Xu |
| 2011 | Interspeech | Response Probability Based Decoding Algorithm for Large Vocabulary Continuous Speech Recognition. | Zhanlei Yang, Hao Chao, Wenju Liu |
| 2011 | Interspeech | Monaural Voiced Speech Segregation Based on Pitch and Comb Filter. | Xueliang Zhang, Wenju Liu |
| 2010 | ICPR | Learning GMM Using Elliptically Contoured Distributions. | Bo Li, Wenju Liu, Lihua Dou |
| 2010 | IJCNN | Mandarin stress detection using hierarchical model based boosting classification and regression tree. | Chong-Jia Ni, Wenju Liu, Bo Xu |
| 2010 | Interspeech | Masking property based microphone array post-filter design. | Ning Cheng, Wenju Liu, Lan Wang |
| 2010 | Interspeech | Using prosody to improve Mandarin automatic speech recognition. | Chong-Jia Ni, Wenju Liu, Bo Xu |
| 2010 | Interspeech | A novel path extension framework using steady segment detection for Mandarin speech recognition. | Zhanlei Yang, Wenju Liu |
| 2009 | ICASSP | Monaural voiced speech segregation based on elaborate harmonic grouping strategy. | Xueliang Zhang, Wenju Liu, Peng Li, Bo Xu |
| 2009 | ISNN | Research on Segment Acoustic Model Based Mandarin LVCSR. | Wenju Liu, Yun Tang, Shouye Peng |
| 2009 | ISNN | Accelerating Segment Model Decoding for LVCSR by Parallel Processing of Neighboring Segments. | Shouye Peng, Wenju Liu, Hua Zhang |
| 2009 | ISNN | An Improvement of HSMM-Based Speech Synthesis by Duration-Dependent State Transition Probabilities. | Jing Tao, Wenju Liu |
| 2008 | IJCNN | Fast and robust stochastic segment model for Mandarin digital string recognition. | Wenju Liu, Yun Tang, Shouye Peng |
| 2008 | Interspeech | An effective microphone array post-filter in arbitrary environments. | Ning Cheng, Wenju Liu, Peng Li, Bo Xu |
| 2007 | Interspeech | Context constrained-generalized posterior probability for verifying phone transcriptions. | Hua Zhang, Lijuan Wang, Frank K. Soong, Wenju Liu |
| 2006 | ICASSP | One-Pass Coarse-to-Fine Segmental Speech Decoding Algorithm. | Yun Tang, Wenju Liu, Hua Zhang, Bo Xu, Guo-Hong Ding |
| 2006 | Interspeech | Selective-LPC based representation of STRAIGHT spectrum and its applications in spectral smoothing. | Heng Kang, Wenju Liu |
| 2005 | ICMLC | Mandarin Voice Conversion Using Tone Codebook Mapping. | Guoyu Zuo, Yao Chen, Xiaogang Ruan, Wenju Liu |
| 2004 | Interspeech | Improving performance of text-independent speaker identification by utilizing contextual principal curves filtering. | Yong Guan, Wenju Liu, Hongwei Qi, Jue Wang |
| 2002 | ICASSP | Pitch and tone's modeling in parametric trajectory model. | Yiyan Zhang, Wenju Liu, Bo Xu, Huayun Zhang |
| 2002 | Interspeech | Improving parametric trajectory modeling by integration of pitch and tone information. | Yiyan Zhang, Wenju Liu, Bo Xu, Huayun Zhang |
| 1997 | UAI | Region-Based Approximations for Planning in Stochastic Domains. | Nevin Lianwen Zhang, Wenju Liu |