Ji Ming

According to our database, Ji Ming authored at least 91 papers between 1990 and 2023.

Collaborative distances:

• Dijkstra number of three.
• Erdős number of four.

2023

Multi-channel auto-encoders for learning domain invariant representations enabling superior classification of histopathology images.

Andrew D. Moyes, Richard Gault, Kun Zhang, Ji Ming, Danny Crookes, Jing Wang

Medical Image Anal., 2023

2021

Multi-Channel Auto-Encoders and a Novel Dataset for Learning Domain Invariant Representations of Histopathology Images.

Andrew D. Moyes, Richard Gault, Kun Zhang, Ji Ming, Danny Crookes, Jing Wang

CoRR, 2021

2019

Matching Larger Image Areas for Unconstrained Face Identification.

Jack Gaston, Ji Ming, Danny Crookes

IEEE Trans. Cybern., 2019

Full-Sentence Correlation: A Method to Handle Unpredictable Noise for Robust Speech Recognition.

Ji Ming, Danny Crookes

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

2018

Speech Segment Clustering for Real-Time Exemplar-Based Speech Enhancement.

David Nesbitt, Danny Crookes, Ji Ming

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017

Largest Matching Areas for Illumination and Occlusion Robust Face Recognition.

Niall McLaughlin, Ji Ming, Danny Crookes

IEEE Trans. Cybern., 2017

Speech Enhancement Based on Full-Sentence Correlation and Clean Speech Recognition.

Ji Ming, Danny Crookes

IEEE ACM Trans. Audio Speech Lang. Process., 2017

2016

Hysteresis compensation for piezoelectric laser scanner with open-loop control method.

Chen Wei, Ji Ming, Zhu Lei, Guohua Jiao, Jiancheng Lv

Proceedings of the IEEE International Conference on Real-time Computing and Robotics, 2016

Research of Large-Scale Terrain Data Organization Method in Virtual Reality.

Gao Qiang, Ji Ming, Pang Lan, Wang Xiao-Tian, Li Jie, Wang Ma-Qiang

Proceedings of the 9th International Symposium on Computational Intelligence and Design, 2016

Wide matching - An approach to improving noise robustness for speech enhancement.

Ji Ming, Danny Crookes

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

A largest matching area approach to image denoising.

Jack Gaston, Ji Ming, Danny Crookes

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

2014

Robust Audio-Visual Speech Recognition Under Noisy Audio-Video Conditions.

Darryl Stewart, Rowan Seymour, Adrian Pass, Ji Ming

IEEE Trans. Cybern., 2014

An iterative longest matching segment approach to speech enhancement with additive noise and channel distortion.

Ji Ming, Danny Crookes

Comput. Speech Lang., 2014

Speech enhancement from additive noise and channel distortion - a corpus-based approach.

Ji Ming, Danny Crookes

Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

2013

Robust Multimodal Person Identification With Limited Training Data.

Niall McLaughlin, Ji Ming, Danny Crookes

IEEE Trans. Hum. Mach. Syst., 2013

CLOSE - A Data-Driven Approach to Speech Separation.

Ji Ming, Ramji Srinivasan, Danny Crookes, Ayeh Jafari

IEEE Trans. Speech Audio Process., 2013

2012

Unconstrained Speech Separation by Composition of Longest Segments.

Ji Ming, Ramji Srinivasan, Danny Crookes

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

Single-channel speaker-pair identification: A new approach based on automatic frame selection.

Ramji Srinivasan, Ji Ming, Danny Crookes

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

Illumination invariant facial recognition using a piecewise-constant lighting model.

Niall McLaughlin, Ji Ming, Danny Crookes

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

2011

A Corpus-Based Approach to Speech Enhancement From Nonstationary Noise.

Ji Ming, Ramji Srinivasan, Danny Crookes

IEEE Trans. Speech Audio Process., 2011

Creating a Spontaneous Conversational Speech Corpus.

Maria Husin, Darryl Stewart, Ji Ming, Francis Jack Smith

Data Sci. J., 2011

Robust Bimodal Person Identification Using Face and Speech with Limited Training Data and Corruption of Both Modalities.

Niall McLaughlin, Ji Ming, Danny Crookes

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

A Longest Matching Segment Approach with Baysian Adaptation - Application to Noise-Robust Speaker Recognition.

Ayeh Jafari, Ramji Srinivasan, Danny Crookes, Ji Ming

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Speaker recognition in noisy conditions with limited training data.

Niall McLaughlin, Ji Ming, Danny Crookes

Proceedings of the 19th European Signal Processing Conference, 2011

Exploiting long-range temporal dynamics of speech for noise-robust speaker recognition.

Ayeh Jafari, Ramji Srinivasan, Danny Crookes, Ji Ming

Proceedings of the 19th European Signal Processing Conference, 2011

2010

Combining missing-feature theory, speech enhancement, and speaker-dependent/-independent modeling for speech separation.

Ji Ming, Timothy J. Hazen, James R. Glass

Comput. Speech Lang., 2010

A longest matching segment approach for text-independent speaker recognition.

Ayeh Jafari, Ramji Srinivasan, Danny Crookes, Ji Ming

Proceedings of the 11th Annual Conference of the International Speech Communication Association, 2010

Inter-frame contextual modelling for visual speech recognition.

Adrian Pass, Ji Ming, Philip Hanna, Jianguo Zhang, Darryl Stewart

Proceedings of the International Conference on Image Processing, 2010

Adapting noisy speech models - Extended uncertainty decoding.

Jianhua Lu, Ji Ming, Roger F. Woods

Proceedings of the IEEE International Conference on Acoustics, 2010

2009

Extending Zipf's law to <i>n</i>-grams for large corpora.

Le Quan Ha, Philip Hanna, Ji Ming, Francis Jack Smith

Artif. Intell. Rev., 2009

Replacing uncertainty decoding with subband re-estimation for large vocabulary speech recognition in noise.

Jianhua Lu, Ji Ming, Roger F. Woods

Proceedings of the 10th Annual Conference of the International Speech Communication Association, 2009

Maximizing the continuity in segmentation - A new approach to model, segment and recognize speech.

Ji Ming

Proceedings of the IEEE International Conference on Acoustics, 2009

Robust face recognition with partially occluded images based on a single or a small number of training samples.

Jie Lin, Ji Ming, Danny Crookes

Proceedings of the IEEE International Conference on Acoustics, 2009

2008

Comparison of Image Transform-Based Features for Visual Speech Recognition in Clean and Corrupted Videos.

Rowan Seymour, Darryl Stewart, Ji Ming

EURASIP J. Image Video Process., 2008

Combining noise compensation and missing-feature decoding for large vocabulary speech recognition in noise.

Jianhua Lu, Ji Ming, Roger F. Woods

Proceedings of the 9th Annual Conference of the International Speech Communication Association, 2008

Modeling long-range dependencies in speech data for text-independent speaker recognition.

Ji Ming, Jie Lin

Proceedings of the IEEE International Conference on Acoustics, 2008

A probabilistic union approach to robust face recognition with partial distortion and occlusion.

Jie Lin, Ji Ming, Danny Crookes

Proceedings of the IEEE International Conference on Acoustics, 2008

2007

Robust Speaker Recognition in Noisy Conditions.

Ji Ming, Timothy J. Hazen, James R. Glass, Douglas A. Reynolds

IEEE Trans. Speech Audio Process., 2007

Audio-visual integration for robust speech recognition using maximum weighted stream posteriors.

Rowan Seymour, Darryl Stewart, Ji Ming

Proceedings of the 8th Annual Conference of the International Speech Communication Association, 2007

2006

Noise compensation for speech recognition with arbitrary additive noise.

Ji Ming

IEEE Trans. Speech Audio Process., 2006

A Posterior Union Model with Applications to Robust Speech and Speaker Recognition.

Ji Ming, Jie Lin, Francis Jack Smith

EURASIP J. Adv. Signal Process., 2006

A Comparative Study of Methods for Handheld Speaker Verification in Realistic Noisy Conditions.

Ji Ming, Timothy J. Hazen, James R. Glass

Proceedings of the Odyssey 2006: The Speaker and Language Recognition Workshop, 2006

Speaker Verification Over Handheld Devices with Realistic Noisy Speech Data.

Ji Ming, Timothy J. Hazen, James R. Glass

Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006

2005

Subband Correlation and Robust Speech Recognition.

James McAuley, Ji Ming, Darryl Stewart, Philip Hanna

IEEE Trans. Speech Audio Process., 2005

A posteriori multiple word-domain language model.

Elvira I. Sicilia-Garcia, Ji Ming, Francis Jack Smith

Proceedings of the 9th European Conference on Speech Communication and Technology, 2005

A new posterior based audio-visual integration method for robust speech recognition.

Rowan Seymour, Ji Ming, Darryl Stewart

Proceedings of the 9th European Conference on Speech Communication and Technology, 2005

Speaker verification in noisy conditions using correlated subband features.

James McAuley, Ji Ming, Pat Corr

Proceedings of the 9th European Conference on Speech Communication and Technology, 2005

Speaker Identification in Unknown Noisy Conditions - A Universal Compensation Approach.

Ji Ming, Darryl Stewart, Saeed Vaseghi

Proceedings of the 2005 IEEE International Conference on Acoustics, 2005

2004

Evaluation of universal compensation on Aurora 2 and 3 and beyond.

Ji Ming, Baochun Hou

Proceedings of the 8th International Conference on Spoken Language Processing, 2004

Universal compensation - an approach to noisy speech recognition assuming no knowledge of noise.

Ji Ming

Proceedings of the 2004 IEEE International Conference on Acoustics, 2004

Modeling sub-band correlation for noise-robust speech recognition.

James McAuley, Ji Ming, Philip Hanna, Darryl Stewart

Proceedings of the 2004 IEEE International Conference on Acoustics, 2004

2003

Extension of Zipf's Law to Word and Character N-grams for English and Chinese.

Le Quan Ha, Elvira I. Sicilia-Garcia, Ji Ming, Francis Jack Smith

Int. J. Comput. Linguistics Chin. Lang. Process., 2003

Speech recognition with unknown partial feature corruption - a review of the union model.

Ji Ming, Francis Jack Smith

Comput. Speech Lang., 2003

Study on complex system based on the brittleness.

Wei Qi, Jin Hongzhang, Guo Jian, Ji Ming

Proceedings of the IEEE International Conference on Systems, 2003

Robust speaker identification using posterior union models.

Ji Ming, Darryl Stewart, Philip Hanna, Pat Corr, Francis Jack Smith, Saeed Vaseghi

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

A posterior union model for improved robust speech recognition in nonstationary noise.

Ji Ming, Francis Jack Smith

Proceedings of the 2003 IEEE International Conference on Acoustics, 2003

2002

Robust speech recognition using probabilistic union models.

Ji Ming, Peter Jancovic, Francis Jack Smith

IEEE Trans. Speech Audio Process., 2002

Individual word language models and the frequency approach.

Elvira I. Sicilia-Garcia, Ji Ming, Francis Jack Smith

Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

Combining the union model and missing feature method to improve noise robustness in ASR.

Peter Jancovic, Ji Ming

Proceedings of the IEEE International Conference on Acoustics, 2002

Extension of Zipf's Law to Words and Phrases.

Le Quan Ha, Elvira I. Sicilia-Garcia, Ji Ming, Francis Jack Smith

Proceedings of the 19th International Conference on Computational Linguistics, 2002

2001

Union: A new approach for combining sub-band observations for noisy speech recognition.

Ji Ming, Francis Jack Smith

Speech Commun., 2001

Union: a model for partial temporal corruption of speech.

Ji Ming, Francis Jack Smith

Comput. Speech Lang., 2001

Triggering individual word domains in n-gram language models.

Elvira I. Sicilia-Garcia, Ji Ming, Francis Jack Smith

Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

Modeling the mixtures of known noise and unknown unexpected noise for robust speech recognition.

Ji Ming, Peter Jancovic, Philip Hanna, Darryl Stewart

Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

A multi-band approach based on the probabilistic union model and frequency-filtering features for robust speech recognition.

Peter Jancovic, Ji Ming

Proceedings of the EUROSPEECH 2001 Scandinavia, 2001

2000

Combining Multi-band and Frequency-Filtering Techniques for Speech Recognition in Noisy Environments.

Peter Jancovic, Ji Ming, Philip Hanna, Darryl Stewart, Francis Jack Smith

Proceedings of the Text, Speech and Dialogue - Third International Workshop, 2000

Robust feature selection using probabilistic union models.

Ji Ming, Peter Jancovic, Philip Hanna, Darryl Stewart, Francis Jack Smith

Proceedings of the Sixth International Conference on Spoken Language Processing, 2000

Improved lexicon formation through removal of co-articulation and acoustic recognition errors.

Philip Hanna, Darryl Stewart, Ji Ming, Francis Jack Smith

Proceedings of the Sixth International Conference on Spoken Language Processing, 2000

Discrete Chebyshev Transform - A Natural Modification of the DCT.

Pat Corr, Darryl Stewart, Philip Hanna, Ji Ming, Francis Jack Smith

Proceedings of the 15th International Conference on Pattern Recognition, 2000

A probabilistic union model for sub-band based robust speech recognition.

Ji Ming, Francis Jack Smith

Proceedings of the IEEE International Conference on Acoustics, 2000

Union: A model for speech recognition subjected to partial and temporal corruption with unknown, time-varying noise statistics.

Ji Ming, Philip Hanna, Darryl Stewart, Peter Jancovic, Francis Jack Smith

Proceedings of the 10th European Signal Processing Conference, 2000

A Dynamic Language Model Based on Individual Word Domains.

Elvira I. Sicilia-Garcia, Ji Ming, Francis Jack Smith

Proceedings of the COLING 2000, 18th International Conference on Computational Linguistics, Proceedings of the Conference, 2 Volumes, July 31, 2000

1999

A Bayesian approach for building triphone models for continuous speech recognition.

Ji Ming, Peter O'Boyle, Marie Owens, Francis Jack Smith

IEEE Trans. Speech Audio Process., 1999

Inter-frame dependence arising from preceding and succeeding frames - Application to speech recognition.

Philip Hanna, Ji Ming, Francis Jack Smith

Speech Commun., 1999

Adaptive Parameter Training in an Interpolated N-gram Language Model.

Peter O'Boyle, Ji Ming, Marie Owens, Francis Jack Smith

J. Quant. Linguistics, 1999

A Bayesian triphone model.

Ji Ming, Francis Jack Smith

Comput. Speech Lang., 1999

A missing-word test comparison of human and statistical language model performance.

Marie Owens, Anja Kürger, Paul Gerard Donnelly, Francis Jack Smith, Ji Ming

Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

The application of an improved DP match for automatic lexicon generation.

Philip Hanna, Darryl Stewart, Ji Ming

Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

Language modelling with hierarchical domains.

Paul Gerard Donnelly, Francis Jack Smith, Elvira I. Sicilia-Garcia, Ji Ming

Proceedings of the Sixth European Conference on Speech Communication and Technology, 1999

Improving speech recognition performance by using multi-model approaches.

Ji Ming, Philip Hanna, Darryl Stewart, Marie Owens, Francis Jack Smith

Proceedings of the 1999 IEEE International Conference on Acoustics, 1999

1998

Capturing discriminative information using multiple modeling techniques.

Ji Ming, Philip Hanna, Darryl Stewart, Saeed Vaseghi, Francis Jack Smith

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

Improved phone recognition using Bayesian triphone models.

Ji Ming, Francis Jack Smith

Proceedings of the 1998 IEEE International Conference on Acoustics, 1998

A Bayesian triphone model with parameter tying.

Ji Ming, Marie Owens, Francis Jack Smith

Proceedings of the 9th European Signal Processing Conference, 1998

1997

From phone identification to phone clustering using mutual information.

Peter O'Boyle, Ji Ming, Marie Owens, Francis Jack Smith

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

Modelling inter-frame dependence with preceeding and succeeding frames.

Philip Hanna, Ji Ming, Peter O'Boyle, Francis Jack Smith

Proceedings of the Fifth European Conference on Speech Communication and Technology, 1997

1996

Modelling of the interframe dependence in an HMM using conditional Gaussian mixtures.

Ji Ming, Francis Jack Smith

Comput. Speech Lang., 1996

Speech recognition using a strong correlation assumption for the instantaneous spectra.

Ji Ming, Peter O'Boyle, John G. McMahon, Francis Jack Smith

Proceedings of the 4th International Conference on Spoken Language Processing, 1996

Improving n-gram models by incorporating enhanced distributions.

Peter O'Boyle, Ji Ming, John G. McMahon, Francis Jack Smith

Proceedings of the 1996 IEEE International Conference on Acoustics, 1996

1995

An HMM with optimized segment-dependent observations for speech recognition.

Ji Ming, Peter O'Boyle, Francis Jack Smith

Proceedings of the Fourth European Conference on Speech Communication and Technology, 1995

A hidden Markov model with optimized inter-frame dependence.

Francis Jack Smith, Ji Ming, Peter O'Boyle, A. D. Irvine

Proceedings of the 1995 International Conference on Acoustics, 1995

1990

The statistical information formulation for noisy speech recognition.

Ji Ming

Proceedings of the 10th IAPR International Conference on Pattern Recognition, 1990