| 2023 | ICASSP | Joint Estimation of DOA and Distance in Noisy Reverberant Conditions. | Suliang Bu, Tuo Zhao, Yunxin Zhao |
| 2022 | ICASSP | Enhance Rnnlms with Hierarchical Multi-Task Learning for ASR. | Minguang Song, Yunxin Zhao |
| 2022 | Interspeech | Steering vector correction in MVDR beamformer for speech enhancement. | Suliang Bu, Yunxin Zhao, Tuo Zhao |
| 2021 | Interspeech | Learning Speech Structure to Improve Time-Frequency Masks. | Suliang Bu, Yunxin Zhao, Shaojun Wang, Mei Han |
| 2020 | ICASSP | Learning Recurrent Neural Network Language Models With Context-Sensitive Label Smoothing for Automatic Speech Recognition. | Minguang Song, Yunxin Zhao, Shaojun Wang, Mei Han |
| 2019 | Interspeech | A Novel Method to Correct Steering Vectors in MVDR Beamformer for Noise Robust ASR. | Suliang Bu, Yunxin Zhao, Mei-Yuh Hwang |
| 2018 | AAAI | Slim Embedding Layers for Recurrent Neural Language Models. | Zhongliang Li, Raymond Kulhanek, Shaojun Wang, Yunxin Zhao, Shuang Wu |
| 2018 | Interspeech | A Probability Weighted Beamformer for Noise Robust ASR. | Suliang Bu, Yunxin Zhao, Mei-Yuh Hwang, Sining Sun |
| 2017 | ICASSP | Exploiting different word clusterings for class-based RNN language modeling in speech recognition. | Minguang Song, Yunxin Zhao, Shaojun Wang |
| 2015 | ICASSP | A novel static parameter calculation method for model compensation. | Suliang Bu, Yunxin Zhao, Yanmin Qian, Kai Yu |
| 2015 | Interspeech | Time-frequency kernel-based CNN for speech recognition. | Tuo Zhao, Yunxin Zhao, Xin Chen |
| 2012 | Interspeech | Modulation domain blind source separation for noisy speech mixture. | Yi Zhang, Yunxin Zhao |
| 2011 | ICASSP | Clustering of bootstrapped acoustic model with full covariance. | Xin Chen, Xiaodong Cui, Jian Xue, Peder A. Olsen, John R. Hershey, Bowen Zhou, Yunxin Zhao |
| 2011 | ICASSP | Spectral subtraction on real and imaginary modulation spectra. | Yi Zhang, Yunxin Zhao |
| 2011 | Interspeech | On the Effectiveness of Statistical Modeling Based Template Matching Approach for Continuous Speech Recognition. | Xie Sun, Xin Chen, Yunxin Zhao |
| 2011 | Interspeech | New Methods for Template Selection and Compression in Continuous Speech Recognition. | Xie Sun, Yunxin Zhao |
| 2010 | ICASSP | Data sampling ensemble acoustic modelling in speaker independent speech recognition. | Xin Chen, Yunxin Zhao |
| 2010 | Interspeech | Integrating MLP features and discriminative training in data sampling based ensemble acoustic modeling. | Xin Chen, Yunxin Zhao |
| 2010 | Interspeech | Integrate template matching and statistical modeling for speech recognition. | Xie Sun, Yunxin Zhao |
| 2009 | ICASSP | Data sampling based ensemble acoustic modelling. | Xin Chen, Yunxin Zhao |
| 2009 | ICASSP | Semi-tied covariance matrices for acoustic models based on random forests of phonetic decision trees. | Jian Xue, L. Che, Yunxin Zhao |
| 2008 | ICASSP | Random-forests-based phonetic decision trees for conversational speech recognition. | Jian Xue, Yunxin Zhao |
| 2007 | ICASSP | A Bayesian Approach for Phonetic Decision Tree State Tying in Conversational Speech Recognition. | Rusheng Hu, Yunxin Zhao |
| 2006 | ICASSP | Gradient Boosting Learning of Hidden Markov Models. | Rusheng Hu, Xiaolong Li, Yunxin Zhao |
| 2006 | ICASSP | Fast Noise Compensation for Speech Separation in Diffuse Noise. | Rong Hu, Yunxin Zhao |
| 2006 | ICASSP | Random Forests-Based Confidence Annotation Using Novel Features from Confusion Network. | Jian Xue, Yunxin Zhao |
| 2006 | ICASSP | An Automatic Captioning System for Telemedicine. | Yunxin Zhao, Xiaojia Zhang, Rusheng Hu, Jian Xue, Xiaolong Li, Lili Che, Rong Hu, Laura Schopp |
| 2006 | Interspeech | Bayesian decision tree state tying for conversational speech recognition. | Rusheng Hu, Yunxin Zhao |
| 2006 | Interspeech | Adaptive speech enhancement for speech separation in diffuse noise. | Rong Hu, Yunxin Zhao |
| 2006 | Interspeech | New improvements in decoding speed and latency for automatic captioning. | Jian Xue, Rusheng Hu, Yunxin Zhao |
| 2005 | ICASSP | Acoustic Model Training Using Greedy EM. | Rusheng Hu, Xiaolong Li, Yunxin Zhao |
| 2005 | ICASSP | Adaptive Decorrelation Filtering Algorithm for Speech Source Separation in Uncorrelated Noises. | Rong Hu, Yunxin Zhao |
| 2005 | ICASSP | Improved Confusion Network Algorithm and Shortest Path Search from Word Lattice. | Jian Xue, Yunxin Zhao |
| 2005 | Interspeech | Incremental largest margin linear regression and MAP adaptation for speech separation in telemedicine applications. | Rusheng Hu, Jian Xue, Yunxin Zhao |
| 2005 | Interspeech | Variable step size adaptive decorrelation filtering for competing speech separation. | Rong Hu, Yunxin Zhao |
| 2004 | ICASSP | Prior knowledge guided MEL based model selection and adaptation for nonnative speech recognition. | Xiaodong He, Yunxin Zhao |
| 2004 | ICASSP | Fast convergence speech source separation in reverberant acoustic environment. | Yunxin Zhao, Rong Hu |
| 2003 | ICASSP | Semantic n-gram language modeling with the latent maximum entropy principle. | Shaojun Wang, Dale Schuurmans, Fuchun Peng, Yunxin Zhao |
| 2003 | ICML | Learning Mixture Models with the Latent Maximum Entropy Principle. | Shaojun Wang, Dale Schuurmans, Fuchun Peng, Yunxin Zhao |
| 2003 | Interspeech | Exploiting order-preserving perfect hashing to speedup n-gram language model lookahead. | Xiaolong Li, Yunxin Zhao |
| 2003 | UAI | Boltzmann Machine Learning with the Latent Maximum Entropy Principle. | Shaojun Wang, Dale Schuurmans, Fuchun Peng, Yunxin Zhao |
| 2002 | ICASSP | Fast model adaptation and complexity selection for nonnative English speakers. | Xiaodong He, Yunxin Zhao |
| 2002 | ICASSP | Co-channel speech separation for assistive listening. | Yunxin Zhao, Kuan-Chieh Yen, Sigfrid D. Soli, Shawn X. Gao, Andy Vermiglio |
| 2002 | Interspeech | Maximum expected likelihood based model selection and adaptation for nonnative English speakers. | Xiaodong He, Yunxin Zhao |
| 2002 | Interspeech | Minimum perfect hashing for fast n-gram language model lookup. | Xiao Zhang, Yunxin Zhao |
| 2001 | ICASSP | Lattice-ladder decorrelation filters developed for co-channel speech separation. | Kuan-Chieh Yen, Yunxin Zhao |
| 2001 | ICASSP | Recursive estimation of time-varying environments for robust speech recognition. | Yunxin Zhao, Shaojun Wang, Kuan-Chieh Yen |
| 2001 | Interspeech | Model complexity optimization for nonnative English speakers. | Xiaodong He, Yunxin Zhao |
| 2000 | ICASSP | On-line Bayesian speaker adaptation using tree-structured transformation and robust priors. | Shaojun Wang, Yunxin Zhao |
| 2000 | ICASSP | Lattice-ladder structured adaptive decorrelation filtering for co-channel speech separation. | Kuan-Chieh Yen, Yunxin Zhao |
| 2000 | ICASSP | Maximum likelihood joint estimation of channel and noise for robust speech recognition. | Yunxin Zhao |
| 2000 | Interspeech | Optimal on-line Bayesian model selection for speaker adaptation. | Shaojun Wang, Yunxin Zhao |
| 2000 | Interspeech | A combined adaptive and decision tree based speech separation technique for telemedicine applications. | Yunxin Zhao, Xiao Zhang, Xiaodong He, Laura Schopp |
| 1999 | ICASSP | Adaptive decorrelation filtering for separation of co-channel speech signals from m>2 sources. | Kuan-Chieh Yen, Yunxin Zhao |
| 1999 | Interspeech | A DCT-based fast enhancement technique for robust speech recognition in automobile usage. | Jun Huang, Yunxin Zhao, Stephen E. Levinson |
| 1999 | Interspeech | Co-channel speech separation in the presence of correlated and uncorrelated noises. | Kuan-Chieh Yen, Jun Huang, Yunxin Zhao |
| 1999 | Interspeech | Channel identification and spectrum estimation for robust automatic speech recognition. | Yunxin Zhao |
| 1998 | ICASSP | An energy-constrained signal subspace method for speech enhancement and recognition in colored noise. | Jun Huang, Yunxin Zhao |
| 1998 | ICASSP | Improvements on co-channel speech separation using ADF: low complexity, fast convergence, and generalization. | Kuan-Chieh Yen, Yunxin Zhao |
| 1998 | Interspeech | Robust speech recognition using discriminative stream weighting and parameter interpolation. | Stephen M. Chu, Yunxin Zhao |
| 1998 | Interspeech | Recognizing emotions in speech using short-term and long-term features. | Yang Li, Yunxin Zhao |
| 1997 | ICASSP | Co-channel speech separation for robust automatic speech recognition: stability and efficiency. | Kuan-Chieh Yen, Yunxin Zhao |
| 1997 | ICASSP | Parallel, finite-convergence learning algorithms for relaxation labeling processes. | Xinhua Zhuang, Yunxin Zhao |
| 1997 | MMSP | High performance CELP coder utilizing a novel adaptive forward-backward LPC quantization. | Zijun Yang, Jozsef Vass, Yunxin Zhao, Xinhua Zhuang |
| 1996 | ICASSP | A unification of relaxation labeling and associative memory. | Xinhua Zhuang, Yunxin Zhao |
| 1996 | ICPR | Binary linear decision tree with genetic algorithm. | Bing-Bing Chai, Xinhua Zhuang, Yunxin Zhao, Jack Sklansky |
| 1996 | ICPR | Speech/gesture interface to a visual computing environment for molecular biologists. | Rajeev Sharma, Thomas S. Huang, Vladimir I. Pavlovic, Yunxin Zhao, Zion Lo, Stephen M. Chu, Klaus Schulten |
| 1996 | Interspeech | Robust automatic speech recognition using a multi-channel signal separation front-end. | Kuan-Chieh Yen, Yunxin Zhao |
| 1995 | ICASSP | Iterative self-learning speaker and channel adaptation under various initial conditions. | Yunxin Zhao |
| 1995 | Interspeech | Hierarchical mixture models and phonological rules in open-vocabulary speech recognition. | Yunxin Zhao |
| 1993 | ICASSP | A new speaker adaptation technique using very short calibration speech. | Yunxin Zhao |
| 1993 | Interspeech | Speaker normalization using constrained spectra shifts in auditory filter domain. | Yoshio Ono, Hisashi Wakita, Yunxin Zhao |
| 1993 | Interspeech | Self-learning speaker adaptation based on spectral variation source decomposition. | Yunxin Zhao |
| 1991 | ICASSP | An HMM based speaker-independent continuous speech recognition system with experiments on the TIMIT database. | Yunxin Zhao, Hisashi Wakita, Xinhua Zhuang |
| 1991 | ICASSP | Morphological structuring image decomposition. | Xinhua Zhuang, Yunxin Zhao, Ming-Yee Chiu |
| 1991 | Interspeech | Generate word transcription dictionary from sentence utterances and evaluate its effect on speaker-independent continuous speech recognition. | Yunxin Zhao, Hisashi Wakita, Xinhua Zhuang |
| 1990 | ICASSP | An analog neural net performing multidimensional maximum entropy spectral estimation. | Xinhua Zhuang, Hyonam Joo, Seho Oh, Yunxin Zhao, Thomas S. Huang |
| 1990 | Interspeech | Experiments with a speaker-independent continuous speech recognition system on the timit database. | Yunxin Zhao, Hisashi Wakita |
| 1988 | CVPR | From depth and optical flow to rigid body motion. | Xinhua Zhuang, Robert M. Haralick, Yunxin Zhao |
| 1988 | ICASSP | Application of the Gibbs distribution to hidden Markov modeling in isolated word recognition. | Yunxin Zhao, Les Atlas, Xinhua Zhuang |