Yunxin Zhao

Yi Zhang, Yunxin Zhao: Real and imaginary modulation spectral subtraction for speech enhancement. Speech Communication 55(4): 509-522 (2013)

Xin Chen, Yunxin Zhao: Building Acoustic Model Ensembles by Data Sampling With Enhanced Trainings and Features. IEEE Transactions on Audio, Speech & Language Processing 21(3): 498-507 (2013)

Shaojun Wang, Dale Schuurmans, Yunxin Zhao: The Latent Maximum Entropy Principle. TKDD 6(2): 8 (2012)

Yi Zhang, Yunxin Zhao: Modulation domain blind source separation for noisy speech mixture. INTERSPEECH 2012

Shaojun Wang, Dale Schuurmans, Fuchun Peng, Yunxin Zhao: Boltzmann Machine Learning with the Latent Maximum Entropy Principle. CoRR abs/1212.2514 (2012)

Xin Chen, Xiaodong Cui, Jian Xue, Peder A. Olsen, John R. Hershey, Bowen Zhou, Yunxin Zhao: Clustering of bootstrapped acoustic model with full covariance. ICASSP 2011: 4496-4499

Yi Zhang, Yunxin Zhao: Spectral subtraction on real and imaginary modulation spectra. ICASSP 2011: 4744-4747

Xie Sun, Xin Chen, Yunxin Zhao: On the Effectiveness of Statistical Modeling Based Template Matching Approach for Continuous Speech Recognition. INTERSPEECH 2011: 453-456

Xie Sun, Yunxin Zhao: New Methods for Template Selection and Compression in Continuous Speech Recognition. INTERSPEECH 2011: 985-988

Xin Chen, Yunxin Zhao: Data sampling ensemble acoustic modelling in speaker independent speech recognition. ICASSP 2010: 5130-5133

Xie Sun, Yunxin Zhao: Integrate template matching and statistical modeling for speech recognition. INTERSPEECH 2010: 74-77

Xin Chen, Yunxin Zhao: Integrating MLP features and discriminative training in data sampling based ensemble acoustic modeling. INTERSPEECH 2010: 1349-1352

Xin Chen, Yunxin Zhao: Data sampling based ensemble acoustic modelling. ICASSP 2009: 3805-3808

Jian Xue, L. Che, Yunxin Zhao: Semi-tied covariance matrices for acoustic models based on random forests of phonetic decision trees. ICASSP 2009: 4469-4472

Rong Hu, Yunxin Zhao: Fast Noise Compensation and Adaptive Enhancement for Speech Separation. EURASIP J. Audio, Speech and Music Processing 2008 (2008)

Jian Xue, Yunxin Zhao: Random Forests of Phonetic Decision Trees for Acoustic Modeling in Conversational Speech Recognition. IEEE Transactions on Audio, Speech & Language Processing 16(3): 519-528 (2008)

Jian Xue, Yunxin Zhao: Random-forests-based phonetic decision trees for conversational speech recognition. ICASSP 2008: 4169-4172

Xiaolong Li, Yunxin Zhao: A fast and memory-efficient N-gram language model lookup method for large vocabulary continuous speech recognition. Computer Speech & Language 21(1): 1-25 (2007)

Xiaodong He, Yunxin Zhao: Prior knowledge guided maximum expected likelihood based model selection and adaptation for nonnative speech recognition. Computer Speech & Language 21(2): 247-265 (2007)

Rusheng Hu, Yunxin Zhao: Knowledge-Based Adaptive Decision Tree State Tying for Conversational Speech Recognition. IEEE Transactions on Audio, Speech & Language Processing 15(7): 2160-2168 (2007)

Xiaojia Zhang, Yunxin Zhao, Laura Schopp: A Novel Method of Language Modeling for Automatic Captioning in TC Video Teleconferencing. IEEE Transactions on Information Technology in Biomedicine 11(3): 332-337 (2007)

Yunxin Zhao, Rong Hu, Xiaolong Li: Speedup convergence and reduce noise for enhanced speech separation and recognition. IEEE Transactions on Audio, Speech & Language Processing 14(4): 1235-1244 (2006)

Rusheng Hu, Yunxin Zhao: Bayesian decision tree state tying for conversational speech recognition. INTERSPEECH 2006

Rong Hu, Yunxin Zhao: Adaptive speech enhancement for speech separation in diffuse noise. INTERSPEECH 2006

Jian Xue, Rusheng Hu, Yunxin Zhao: New improvements in decoding speed and latency for automatic captioning. INTERSPEECH 2006

Shaojun Wang, Dale Schuurmans, Fuchun Peng, Yunxin Zhao: Combining Statistical Language Models via the Latent Maximum Entropy Principle. Machine Learning 60(1-3): 229-250 (2005)

Rusheng Hu, Jian Xue, Yunxin Zhao: Incremental largest margin linear regression and MAP adaptation for speech separation in telemedicine applications. INTERSPEECH 2005: 261-264

Rong Hu, Yunxin Zhao: Variable step size adaptive decorrelation filtering for competing speech separation. INTERSPEECH 2005: 2297-2300

Shaojun Wang, Dale Schuurmans, Fuchun Peng, Yunxin Zhao: Learning mixture models with the regularized latent maximum entropy principle. IEEE Transactions on Neural Networks 15(4): 903-916 (2004)

Xiaodong He, Yunxin Zhao: Fast model selection based speaker adaptation for nonnative speech. IEEE Transactions on Speech and Audio Processing 11(4): 298-307 (2003)

Yunxin Zhao, Paul D. Gader, Ping Chen, Yue Zhang: Training DHMMs of mine and clutter to minimize landmine detection errors. IEEE T. Geoscience and Remote Sensing 41(5): 1016-1024 (2003)

Shaojun Wang, Dale Schuurmans, Fuchun Peng, Yunxin Zhao: Learning Mixture Models with the Latent Maximum Entropy Principle. ICML 2003: 784-791

Xiaolong Li, Yunxin Zhao: Exploiting order-preserving perfect hashing to speedup n-gram language model lookahead. INTERSPEECH 2003

Shaojun Wang, Dale Schuurmans, Fuchun Peng, Yunxin Zhao: Boltzmann Machine Learning with the Latent Maximum Entropy Principle. UAI 2003: 567-574

Xiaodong He, Yunxin Zhao: Fast model adaptation and complexity selection for nonnative English speakers. ICASSP 2002: 577-580

Yunxin Zhao, Kuan-Chieh Yen, Sigfrid D. Soli, Shawn X. Gao, Andy Vermiglio: Co-channel speech separation for assistive listening. ICASSP 2002: 1945-1948

Xiaodong He, Yunxin Zhao: Maximum expected likelihood based model selection and adaptation for nonnative English speakers. INTERSPEECH 2002

Xiao Zhang, Yunxin Zhao: Minimum perfect hashing for fast n-gram language model lookup. INTERSPEECH 2002

Shaojun Wang, Yunxin Zhao: Online Bayesian tree-structured transformation of HMMs with optimal model selection for speaker adaptation. IEEE Transactions on Speech and Audio Processing 9(6): 663-677 (2001)

Paul D. Gader, Miroslaw Mystkowski, Yunxin Zhao: Landmine detection with ground penetrating radar using hidden Markov models. IEEE T. Geoscience and Remote Sensing 39(6): 1231-1244 (2001)

Yunxin Zhao: Spectrum estimation of short-time stationary signals in additive noise and channel distortion. IEEE Transactions on Signal Processing 49(7): 1409-1420 (2001)

Xiaodong He, Yunxin Zhao: Model complexity optimization for nonnative English speakers. INTERSPEECH 2001: 1461-1464

Rajeev Sharma, Michael Zeller, Vladimir Pavlovic, Thomas S. Huang, Zion Lo, Stephen M. Chu, Yunxin Zhao, James C. Phillips, Klaus Schulten: Speech/Gesture Interface to a Visual-Computing Environment. IEEE Computer Graphics and Applications 20(2): 29-37 (2000)

Yunxin Zhao: Frequency-domain maximum likelihood estimation for automatic speech recognition in additive and convolutive noises. IEEE Transactions on Speech and Audio Processing 8(3): 255-266 (2000)

Jonathan Huang, Kuan-Chieh Yen, Yunxin Zhao: Subband-based adaptive decorrelation filtering for co-channel speech separation. IEEE Transactions on Speech and Audio Processing 8(4): 402-406 (2000)

Jun Huang, Yunxin Zhao: A DCT-based fast signal subspace technique for robust speech recognition. IEEE Transactions on Speech and Audio Processing 8(6): 747-751 (2000)

Shaojun Wang, Yunxin Zhao: Optimal on-line Bayesian model selection for speaker adaptation. INTERSPEECH 2000: 710-713

Yunxin Zhao, Xiao Zhang, Xiaodong He, Laura Schopp: A combined adaptive and decision tree based speech separation technique for telemedicine applications. INTERSPEECH 2000: 795-798

Kuan-Chieh Yen, Yunxin Zhao: Adaptive co-channel speech separation and recognition. IEEE Transactions on Speech and Audio Processing 7(2): 138-151 (1999)

Yunxin Zhao: An EM algorithm for linear distortion channel estimation based on observations from a mixture of Gaussian sources. IEEE Transactions on Speech and Audio Processing 7(4): 400-413 (1999)

Jun Huang, Yunxin Zhao, Stephen E. Levinson: A DCT-based fast enhancement technique for robust speech recognition in automobile usage. EUROSPEECH 1999

Kuan-Chieh Yen, Jun Huang, Yunxin Zhao: Co-channel speech separation in the presence of correlated and uncorrelated noises. EUROSPEECH 1999

Yunxin Zhao: Channel identification and spectrum estimation for robust automatic speech recognition. EUROSPEECH 1999

Jun Huang, Yunxin Zhao: An energy-constrained signal subspace method for speech enhancement and recognition in white and colored noises. Speech Communication 26(3): 165-181 (1998)

Hongchi Shi, Yunxin Zhao, Xinhua Zhuang: A general model for bidirectional associative memories. IEEE Transactions on Systems, Man, and Cybernetics, Part B 28(4): 511-519 (1998)

Stephen M. Chu, Yunxin Zhao: Robust speech recognition using discriminative stream weighting and parameter interpolation. ICSLP 1998

Yang Li, Yunxin Zhao: Recognizing emotions in speech using short-term and long-term features. ICSLP 1998

Jozsef Vass, Yunxin Zhao, Xinhua Zhuang: Adaptive forward-backward quantizer for low bit rate high-quality speech coding. IEEE Transactions on Speech and Audio Processing 5(6): 552-557 (1997)

Michael Zeller, James C. Phillips, A. Dalke, W. Humphrey, Klaus Schulten, Thomas S. Huang, Vladimir Pavlovic, Yunxin Zhao, Zion Lo, Stephen M. Chu, Rajeev Sharma: A Visual Computing Environment for Very Large Scale Biomolecular Modeling. ASAP 1997: 3-

Bing-Bing Chai, Tong Huang, Xinhua Zhuang, Yunxin Zhao, Jack Sklansky: Piecewise linear classifiers using binary tree structure and genetic algorithm. Pattern Recognition 29(11): 1905-1917 (1996)

Yunxin Zhao: Self-learning speaker and channel adaptation based on spectral variation source decomposition. Speech Communication 18(1): 65-77 (1996)

Xinhua Zhuang, Yan Huang, Kannappan Palaniappan, Yunxin Zhao: Gaussian mixture density modeling, decomposition, and applications. IEEE Transactions on Image Processing 5(9): 1293-1302 (1996)

Kuan-Chieh Yen, Yunxin Zhao: Robust automatic speech recognition using a multi-channel signal separation front-end. ICSLP 1996

Yunxin Zhao, Xinhua Zhuang, Sheu-Jen Ting: Gaussian mixture density modeling of non-Gaussian source for autoregressive process. IEEE Transactions on Signal Processing 43(4): 894-903 (1995)

Yunxin Zhao: Hierarchical mixture models and phonological rules in open-vocabulary speech recognition. EUROSPEECH 1995

Yunxin Zhao: An acoustic-phonetic-based speaker adaptation technique for improving speaker-independent continuous speech recognition. IEEE Transactions on Speech and Audio Processing 2(3): 380-394 (1994)

Yunxin Zhao: A speaker-independent continuous speech recognition system using continuous mixture Gaussian density HMM of phoneme-sized units. IEEE Transactions on Speech and Audio Processing 1(3): 345-361 (1993)

Yoshio Ono, Hisashi Wakita, Yunxin Zhao: Speaker normalization using constrained spectra shifts in auditory filter domain. EUROSPEECH 1993

Yunxin Zhao: Self-learning speaker adaptation based on spectral variation source decomposition. EUROSPEECH 1993

Yunxin Zhao, Xinhua Zhuang, Les E. Atlas, Lars Anderson: Parameter estimation and restoration of noisy images using Gibbs distributions in hidden Markov models. CVGIP: Graphical Model and Image Processing 54(3): 187-197 (1992)

Xinhua Zhuang, Yunxin Zhao, Thomas S. Huang: A neural net algorithm for multidimensional maximum entropy spectrum estimation. Neural Networks 4(5): 619-626 (1991)

Yunxin Zhao, Les E. Atlas, Xinhua Zhuang: Application of the Gibbs distribution to hidden Markov modeling in speaker independent isolated word recognition. IEEE Transactions on Signal Processing 39(6): 1291-1299 (1991)

Xinhua Zhuang, Robert M. Haralick, Yunxin Zhao: Maximum entropy image reconstruction. IEEE Transactions on Signal Processing 39(6): 1478-1480 (1991)

Yunxin Zhao, Hisashi Wakita, Xinhua Zhuang: Generate word transcription dictionary from sentence utterances and evaluate its effect on speaker-independent continuous speech recognition. EUROSPEECH 1991

Yunxin Zhao, Hisashi Wakita: Experiments with a speaker-independent continuous speech recognition system on the timit database. ICSLP 1990