Yunxin Zhao

According to our database1, Yunxin Zhao authored at least 135 papers between 1988 and 2021.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Other 

Links

On csauthors.net:

Bibliography

2021
Word Similarity Based Label Smoothing in Rnnlm Training for ASR.
Proceedings of the IEEE Spoken Language Technology Workshop, 2021

UNet++-Based Multi-Channel Speech Dereverberation and Distant Speech Recognition.
Proceedings of the 12th International Symposium on Chinese Spoken Language Processing, 2021

2020
Voice Conversion for Persons with Amyotrophic Lateral Sclerosis.
IEEE J. Biomed. Health Informatics, 2020

Rapid Identification of X-ray Diffraction Patterns Based on Very Limited Data by Interpretable Convolutional Neural Networks.
J. Chem. Inf. Model., 2020

Learning Recurrent Neural Network Language Models With Context-Sensitive Label Smoothing for Automatic Speech Recognition.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019
A Novel Method to Correct Steering Vectors in MVDR Beamformer for Noise Robust ASR.
Proceedings of the Interspeech 2019, 2019

DeepDDK: A Deep Learning based Oral-Diadochokinesis Analysis Software.
Proceedings of the 2019 IEEE EMBS International Conference on Biomedical & Health Informatics, 2019

GLSNet: Global and Local Streams Network for 3D Point Cloud Classification.
Proceedings of the 48th IEEE Applied Imagery Pattern Recognition Workshop, 2019

2018
Structured Sparse Spectral Transforms and Structural Measures for Voice Conversion.
IEEE ACM Trans. Audio Speech Lang. Process., 2018

Multi-Objective Multi-Task Learning on RNNLM for Speech Recognition.
Proceedings of the 2018 IEEE Spoken Language Technology Workshop, 2018

A Robust Nonlinear Microphone Array Postfilter for Noise Reduction.
Proceedings of the 16th International Workshop on Acoustic Signal Enhancement, 2018

A Probability Weighted Beamformer for Noise Robust ASR.
Proceedings of the Interspeech 2018, 2018

Slim Embedding Layers for Recurrent Neural Language Models.
Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018

2017
Exploiting different word clusterings for class-based RNN language modeling in speech recognition.
Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

2016
Ensemble Acoustic Modeling for CD-DNN-HMM Using Random Forests of Phonetic Decision Trees.
J. Signal Process. Syst., 2016

A collaborative control framework with multi-leaders for AUVs based on unscented particle filter.
J. Frankl. Inst., 2016

2015
Time-frequency kernel-based CNN for speech recognition.
Proceedings of the INTERSPEECH 2015, 2015

A novel static parameter calculation method for model compensation.
Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

2014
Integrated exemplar-based template matching and statistical modeling for continuous speech recognition.
EURASIP J. Audio Speech Music. Process., 2014

Building an ensemble of CD-DNN-HMM acoustic model using random forests of phonetic decision trees.
Proceedings of the 9th International Symposium on Chinese Spoken Language Processing, 2014

Multilevel sampling and aggregation for discriminative training.
Proceedings of the 9th International Symposium on Chinese Spoken Language Processing, 2014

2013
Building Acoustic Model Ensembles by Data Sampling With Enhanced Trainings and Features.
IEEE Trans. Speech Audio Process., 2013

Modulation domain blind speech separation in noisy environments.
Speech Commun., 2013

Real and imaginary modulation spectral subtraction for speech enhancement.
Speech Commun., 2013

2012
The Latent Maximum Entropy Principle.
ACM Trans. Knowl. Discov. Data, 2012

Modulation domain blind source separation for noisy speech mixture.
Proceedings of the INTERSPEECH 2012, 2012

2011
New Methods for Template Selection and Compression in Continuous Speech Recognition.
Proceedings of the INTERSPEECH 2011, 2011

On the Effectiveness of Statistical Modeling Based Template Matching Approach for Continuous Speech Recognition.
Proceedings of the INTERSPEECH 2011, 2011

Spectral subtraction on real and imaginary modulation spectra.
Proceedings of the IEEE International Conference on Acoustics, 2011

Clustering of bootstrapped acoustic model with full covariance.
Proceedings of the IEEE International Conference on Acoustics, 2011

2010
Integrate template matching and statistical modeling for speech recognition.
Proceedings of the INTERSPEECH 2010, 2010

Integrating MLP features and discriminative training in data sampling based ensemble acoustic modeling.
Proceedings of the INTERSPEECH 2010, 2010

Data sampling ensemble acoustic modelling in speaker independent speech recognition.
Proceedings of the IEEE International Conference on Acoustics, 2010

2009
Speech-recognition technology in health care and special-needs assistance [Life Sciences].
IEEE Signal Process. Mag., 2009

Semi-tied covariance matrices for acoustic models based on random forests of phonetic decision trees.
Proceedings of the IEEE International Conference on Acoustics, 2009

Data sampling based ensemble acoustic modelling.
Proceedings of the IEEE International Conference on Acoustics, 2009

2008
Random Forests of Phonetic Decision Trees for Acoustic Modeling in Conversational Speech Recognition.
IEEE Trans. Speech Audio Process., 2008

Fast Noise Compensation and Adaptive Enhancement for Speech Separation.
EURASIP J. Audio Speech Music. Process., 2008

Random-forests-based phonetic decision trees for conversational speech recognition.
Proceedings of the IEEE International Conference on Acoustics, 2008

2007
A Novel Method of Language Modeling for Automatic Captioning in TC Video Teleconferencing.
IEEE Trans. Inf. Technol. Biomed., 2007

Knowledge-Based Adaptive Decision Tree State Tying for Conversational Speech Recognition.
IEEE Trans. Speech Audio Process., 2007

A fast and memory-efficient N-gram language model lookup method for large vocabulary continuous speech recognition.
Comput. Speech Lang., 2007

Prior knowledge guided maximum expected likelihood based model selection and adaptation for nonnative speech recognition.
Comput. Speech Lang., 2007

A Bayesian Approach for Phonetic Decision Tree State Tying in Conversational Speech Recognition.
Proceedings of the IEEE International Conference on Acoustics, 2007

2006
Speedup convergence and reduce noise for enhanced speech separation and recognition.
IEEE Trans. Speech Audio Process., 2006

New improvements in decoding speed and latency for automatic captioning.
Proceedings of the INTERSPEECH 2006, 2006

Adaptive speech enhancement for speech separation in diffuse noise.
Proceedings of the INTERSPEECH 2006, 2006

Bayesian decision tree state tying for conversational speech recognition.
Proceedings of the INTERSPEECH 2006, 2006

An Automatic Captioning System for Telemedicine.
Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006

Random Forests-Based Confidence Annotation Using Novel Features from Confusion Network.
Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006

Fast Noise Compensation for Speech Separation in Diffuse Noise.
Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006

Gradient Boosting Learning of Hidden Markov Models.
Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006

2005
Combining Statistical Language Models via the Latent Maximum Entropy Principle.
Mach. Learn., 2005

Variable step size adaptive decorrelation filtering for competing speech separation.
Proceedings of the INTERSPEECH 2005, 2005

Incremental largest margin linear regression and MAP adaptation for speech separation in telemedicine applications.
Proceedings of the INTERSPEECH 2005, 2005

Improved Confusion Network Algorithm and Shortest Path Search from Word Lattice.
Proceedings of the 2005 IEEE International Conference on Acoustics, 2005

Adaptive Decorrelation Filtering Algorithm for Speech Source Separation in Uncorrelated Noises.
Proceedings of the 2005 IEEE International Conference on Acoustics, 2005

Acoustic Model Training Using Greedy EM.
Proceedings of the 2005 IEEE International Conference on Acoustics, 2005

2004
Learning mixture models with the regularized latent maximum entropy principle.
IEEE Trans. Neural Networks, 2004

Fast convergence speech source separation in reverberant acoustic environment.
Proceedings of the 2004 IEEE International Conference on Acoustics, 2004

Prior knowledge guided MEL based model selection and adaptation for nonnative speech recognition.
Proceedings of the 2004 IEEE International Conference on Acoustics, 2004

2003
Training DHMMs of mine and clutter to minimize landmine detection errors.
IEEE Trans. Geosci. Remote. Sens., 2003

Fast model selection based speaker adaptation for nonnative speech.
IEEE Trans. Speech Audio Process., 2003

Boltzmann Machine Learning with the Latent Maximum Entropy Principle.
Proceedings of the UAI '03, 2003

Exploiting order-preserving perfect hashing to speedup n-gram language model lookahead.
Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

Learning Mixture Models with the Latent Maximum Entropy Principle.
Proceedings of the Machine Learning, 2003

Semantic n-gram language modeling with the latent maximum entropy principle.
Proceedings of the 2003 IEEE International Conference on Acoustics, 2003

2002
Minimum perfect hashing for fast n-gram language model lookup.
Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

Maximum expected likelihood based model selection and adaptation for nonnative English speakers.
Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

Co-channel speech separation for assistive listening.
Proceedings of the IEEE International Conference on Acoustics, 2002

Fast model adaptation and complexity selection for nonnative English speakers.
Proceedings of the IEEE International Conference on Acoustics, 2002

2001
Spectrum estimation of short-time stationary signals in additive noise and channel distortion.
IEEE Trans. Signal Process., 2001

Landmine detection with ground penetrating radar using hidden Markov models.
IEEE Trans. Geosci. Remote. Sens., 2001

Online Bayesian tree-structured transformation of HMMs with optimal model selection for speaker adaptation.
IEEE Trans. Speech Audio Process., 2001

Model complexity optimization for nonnative English speakers.
Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

Recursive estimation of time-varying environments for robust speech recognition.
Proceedings of the IEEE International Conference on Acoustics, 2001

Lattice-ladder decorrelation filters developed for co-channel speech separation.
Proceedings of the IEEE International Conference on Acoustics, 2001

2000
Frequency-domain maximum likelihood estimation for automatic speech recognition in additive and convolutive noises.
IEEE Trans. Speech Audio Process., 2000

A DCT-based fast signal subspace technique for robust speech recognition.
IEEE Trans. Speech Audio Process., 2000

Subband-based adaptive decorrelation filtering for co-channel speech separation.
IEEE Trans. Speech Audio Process., 2000

Speech/Gesture Interface to a Visual-Computing Environment.
IEEE Computer Graphics and Applications, 2000

A combined adaptive and decision tree based speech separation technique for telemedicine applications.
Proceedings of the Sixth International Conference on Spoken Language Processing, 2000

Optimal on-line Bayesian model selection for speaker adaptation.
Proceedings of the Sixth International Conference on Spoken Language Processing, 2000

Maximum likelihood joint estimation of channel and noise for robust speech recognition.
Proceedings of the IEEE International Conference on Acoustics, 2000

Lattice-ladder structured adaptive decorrelation filtering for co-channel speech separation.
Proceedings of the IEEE International Conference on Acoustics, 2000

On-line Bayesian speaker adaptation using tree-structured transformation and robust priors.
Proceedings of the IEEE International Conference on Acoustics, 2000

1999
An EM algorithm for linear distortion channel estimation based on observations from a mixture of Gaussian sources.
IEEE Trans. Speech Audio Process., 1999

Adaptive co-channel speech separation and recognition.
IEEE Trans. Speech Audio Process., 1999

Channel identification and spectrum estimation for robust automatic speech recognition.
Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

Co-channel speech separation in the presence of correlated and uncorrelated noises.
Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

A DCT-based fast enhancement technique for robust speech recognition in automobile usage.
Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

Adaptive decorrelation filtering for separation of co-channel speech signals from m>2 sources.
Proceedings of the 1999 IEEE International Conference on Acoustics, 1999

1998
A general model for bidirectional associative memories.
IEEE Trans. Syst. Man Cybern. Part B, 1998

Channel identification and signal spectrum estimation for robust automatic speech recognition.
IEEE Signal Process. Lett., 1998

An energy-constrained signal subspace method for speech enhancement and recognition in white and colored noises.
Speech Commun., 1998

Recognizing emotions in speech using short-term and long-term features.
Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

Robust speech recognition using discriminative stream weighting and parameter interpolation.
Proceedings of the 5th International Conference on Spoken Language Processing, Incorporating The 7th Australian International Speech Science and Technology Conference, Sydney Convention Centre, Sydney, Australia, 30th November, 1998

Improvements on co-channel speech separation using ADF: low complexity, fast convergence, and generalization.
Proceedings of the 1998 IEEE International Conference on Acoustics, 1998

An energy-constrained signal subspace method for speech enhancement and recognition in colored noise.
Proceedings of the 1998 IEEE International Conference on Acoustics, 1998

1997
Adaptive forward-backward quantizer for low bit rate high-quality speech coding.
IEEE Trans. Speech Audio Process., 1997

Energy-constrained signal subspace method for speech enhancement and recognition.
IEEE Signal Process. Lett., 1997

High performance CELP coder utilizing a novel adaptive forward-backward LPC quantization.
Proceedings of the First IEEE Workshop on Multimedia Signal Processing, 1997

GBAM: a general bidirectional associative memory model.
Proceedings of International Conference on Neural Networks (ICNN'97), 1997

Parallel, finite-convergence learning algorithms for relaxation labeling processes.
Proceedings of the 1997 IEEE International Conference on Acoustics, 1997

Co-channel speech separation for robust automatic speech recognition: stability and efficiency.
Proceedings of the 1997 IEEE International Conference on Acoustics, 1997

A Visual Computing Environment for Very Large Scale Biomolecular Modeling.
Proceedings of the 1997 International Conference on Application-Specific Systems, 1997

1996
Gaussian mixture density modeling, decomposition, and applications.
IEEE Trans. Image Process., 1996

Self-learning speaker and channel adaptation based on spectral variation source decomposition.
Speech Commun., 1996

Piecewise linear classifiers using binary tree structure and genetic algorithm.
Pattern Recognit., 1996

Robust automatic speech recognition using a multi-channel signal separation front-end.
Proceedings of the 4th International Conference on Spoken Language Processing, 1996

Speech/gesture interface to a visual computing environment for molecular biologists.
Proceedings of the 13th International Conference on Pattern Recognition, 1996

Binary linear decision tree with genetic algorithm.
Proceedings of the 13th International Conference on Pattern Recognition, 1996

A general auto-associative memory model.
Proceedings of International Conference on Neural Networks (ICNN'96), 1996

A unification of relaxation labeling and associative memory.
Proceedings of the 1996 IEEE International Conference on Acoustics, 1996

1995
Gaussian mixture density modeling of non-Gaussian source for autoregressive process.
IEEE Trans. Signal Process., 1995

Hierarchical mixture models and phonological rules in open-vocabulary speech recognition.
Proceedings of the Fourth European Conference on Speech Communication and Technology, 1995

Iterative self-learning speaker and channel adaptation under various initial conditions.
Proceedings of the 1995 International Conference on Acoustics, 1995

1994
An acoustic-phonetic-based speaker adaptation technique for improving speaker-independent continuous speech recognition.
IEEE Trans. Speech Audio Process., 1994

1993
A speaker-independent continuous speech recognition system using continuous mixture Gaussian density HMM of phoneme-sized units.
IEEE Trans. Speech Audio Process., 1993

Self-learning speaker adaptation based on spectral variation source decomposition.
Proceedings of the Third European Conference on Speech Communication and Technology, 1993

Speaker normalization using constrained spectra shifts in auditory filter domain.
Proceedings of the Third European Conference on Speech Communication and Technology, 1993

A new speaker adaptation technique using very short calibration speech.
Proceedings of the IEEE International Conference on Acoustics, 1993

1992
Parameter estimation and restoration of noisy images using Gibbs distributions in hidden Markov models.
CVGIP Graph. Model. Image Process., 1992

1991
Maximum entropy image reconstruction.
IEEE Trans. Signal Process., 1991

Application of the Gibbs distribution to hidden Markov modeling in speaker independent isolated word recognition.
IEEE Trans. Signal Process., 1991

A neural net algorithm for multidimensional maximum entropy spectrum estimation.
Neural Networks, 1991

Generate word transcription dictionary from sentence utterances and evaluate its effect on speaker-independent continuous speech recognition.
Proceedings of the Second European Conference on Speech Communication and Technology, 1991

Morphological structuring image decomposition.
Proceedings of the 1991 International Conference on Acoustics, 1991

An HMM based speaker-independent continuous speech recognition system with experiments on the TIMIT database.
Proceedings of the 1991 International Conference on Acoustics, 1991

1990
The use of cone-shaped kernels for generalized time-frequency representations of nonstationary signals.
IEEE Trans. Acoust. Speech Signal Process., 1990

Residual-Based robust estimation and image-motion analysis.
Int. J. Imaging Syst. Technol., 1990

Experiments with a speaker-independent continuous speech recognition system on the timit database.
Proceedings of the First International Conference on Spoken Language Processing, 1990

An analog neural net performing multidimensional maximum entropy spectral estimation.
Proceedings of the 1990 International Conference on Acoustics, 1990

1988
Application of the Gibbs distribution to hidden Markov modeling in isolated word recognition.
Proceedings of the IEEE International Conference on Acoustics, 1988

From depth and optical flow to rigid body motion.
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1988


  Loading...