American Journal of Signal Processing

American Journal of Signal Processing publishes articles on signal processing research and applications. It covers aspects from fundamental principles to practical implementation, intending to bring up-to-date, emerging and active technical developments, issues, and events to the research, educational, and professional communities.

Ming Ji

Editorial Board Member of American Journal of Signal Processing

Professor, School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, UK

Research Areas

Speech, Image and Signal Processing

Education

1988Ph.DBeijing Institute of Technology, Beijing, China
1985M.Phil.Changsha Institute of Technology, Changsha, China
1982B.ScSichuan University, Chengdu, China

Experience

2005-2006Visiting Scientist at the Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge
1993-presentProfessor in the School of Electronics, Electrical Engineering, and Computer Science at Queen's University Belfast
1990-1993Associate Professor with the Department of Electronic Engineering, Changsha Institute of Technology

Publications: Conferences/Workshops/Symposiums/Journals/Books

[1]  Ji Ming, Ramji. Srinivasan, and Danny Crookes, "A corpus-based approach to speech enhancement from nonstationary noise," IEEE Transactions on Audio, Speech and Language Processing, vol. 19, pp. 822-836, 2011. (examples of speech enhancement)
[2]  Jie Lin, Ji Ming, and Danny Crookes, "Robust face recognition with partial occlusion, illumination variation and limited training data by optimal feature selection," IET Computer Vision, vol.5, no. 1, pp. 23-32, 2011.
[3]  Niall McLauhlin, Ji Ming, and Danny Crookes, "Robust bimodal person identification using face and speech With limited training data and corruption of both modalities," Interspeech 2011, Florence, Italy, August 2011.
[4]  Ayeh Jafari, Ramji Srinivasan, Danny Crookes, and Ji Ming, "A longest matching segment approach with Baysian adaptation-application to noise-robust speaker recognition," Interspeech 2011, Florence, Italy, August 2011.
[5]  Ji Ming, Timothy Hazen, and James Glass, "Combining missing-feature theory, speech enhancement, and speaker-dependent/-independent modeling for speech separation," Computer Speech and Language, vol. 24, no. 1, pp. 67-76, 2010.
[6]  Ji Ming, Ramji Srinimasan, and Danny Crookes, "A corpus-based approach to speech enhancement from nonstationary noise," Interspeech 2010, pp. 1097-1100, Makuhari, Japan, September 2010 (best paper in speech enhancement selected by the Technical Program Committee of Interspeech 2010).
[7]  Ayeh Jafari, Ramji Srinimasan, Danny Crookes, and Ji Ming, "A longest matching segment approach for text-independent speaker recognition," Interspeech 2010, pp. 1469-1472, Makuhari, Japan, September 2010.
[8]  Jianhua Lu, Ji Ming, and Roger Woods, "Adapting noisy speech models-extended uncertainty decoding," International Conference on Acoustics, Speech, and Signal Processing (ICASSP'2010), pp. 4322-4325, Dallas, Texas, March 2010.
[9]  Adrian Pass, Ji Ming, Philip Hanna, Jianguo Zhang, Darryl Stewart, "Inter-frame contextual modelling for visual speech recognition," In Proceedings of ICIP'2010, pp.93-96, Hong Kong, China, September 2010.
[10]  Jie Lin, Ji Ming, and Danny Crookes, "Robust face recognition using posterior union model based neural networks," IET Computer Vision, vol. 3, no. 3, pp. 130-142, 2009.
[11]  Jianhua Lu, Ji Ming, Roger Woods, "Replacing Uncertainty Decoding with Subband Re-Estimation for Large Vocabulary Speech Recognition in Noise," Interspeech 2009, pp. 2047-2050, Briton, England, September 2009.
[12]  Jie Lin, Ji Ming, and Danny Crookes, "Robust face recognition with partially occluded images based on a single or a small number of training samples," International Conference on Acoustics, Speech, and Signal Processing (ICASSP'2009), Taipei, Taiwan, April 2009.
[13]  Ji Ming, "Maximizing the continuity in segmentation-a new approach to model, segment and recognize speech," International Conference on Acoustics, Speech, and Signal Processing (ICASSP'2009), Taipei, Taiwan, April 2009.
[14]  R. Seymour, Darryl Stewart and Ji Ming, "Comparison of image transform based features for visual speech recognition in clean and corrupted video," EURASIP Journal on Image and Video Processing, vol. 2008, Article ID 810362, Pages 1-9, 2008.
[15]  Ji Ming, J. Lin, F. J. Smith and T. J. Hazen, "Exploiting Partial Information for Robust Speech and Speaker Recognition," Chapter 8, in book Speech Communication at the Leading Edge, R. H. Yablonski (ed.), pp. 191-207, Nova Publishers, Hauppauge, NY, 2008.
[16]  J. Lu, Ji Ming, and R. Woods, "Combining noise compensation and missing-feature decoding for large vocabulary speech recognition in noise," Interspeech 2008, Brisbane, Australia, September 2008.
[17]  Ji Ming, Jie Lin, "Modeling long-range dependencies in speech data for text-independent speaker recognition," International Conference on Acoustics, Speech, and Signal Processing (ICASSP'2008), pp. 4825-4828, Las Vegas, NV, March 2008.
[18]  J. Lin, Ji Ming, and Danny Crookes, "A probabilistic union approach to robust face recognition with partial distortion and occlusion," International Conference on Acoustics, Speech, and Signal Processing (ICASSP'2008), pp. 993-996, Las Vegas, NV, March 2008.
[19]  Ji Ming, T. J. Hazen, J. R. Glass, and D. A. Reynolds, "Robust speaker recognition in noisy conditions," IEEE Transactions on Audio, Speech, and Language Processing, vol. 15, no. 5, pp. 1711-1723, 2007.
[20]  T. J. Hazen, E. Weinstein, B. Heisele, A. Park, and Ji Ming, "Multi-Modal Face and Speaker Identification for Mobile Devices," Chapter 9, in book Face Biometrics for Personal Identification: Multi-Sensory Multi-Modal Systems, R. I. Hammoud, et al (eds.), pp. 123-138, Springer-Verlag, 2007.
[21]  Ji Ming, and Baochun Hou, "Speech recognition in unknown noisy conditions,"Chapter 11, in book Robust Speech Recognition and Understanding, M. Grimm and K. Kroschel (eds.), pp. 175-186, I-TECH Education and Publishing, 2007.
[22]  Le Quan Ha, P. Hanna, Ji Ming, and F. J. Smith. "Extending Zipf's law to n-grams for large English and Chinese corpora," International Conference on Cognitive Modeling in Linguistics (CML-2007), pp. 161-171, Sofia, Bulgaria, 2007.
[23]  R. Seymour, D. Stewart, and Ji Ming, "Audio-visual integration for robust speech recognition using maximum weighted stream posteriors," Interspeech 2007, Antwerp, Belgium, August 2007.
[24]  Ji Ming, Timothy J. Hazen and James R. Glass, "Combining missing-feature theory, speech enhancement and speaker-dependent/independent modeling for speech separation," International Conference on Spoken Language Processing (ICSLP'2006), pp. 93-96, Pittsburgh, PA, Sep 2006 (Speech Separation Challenge Experimental Examples-click here)
[25]  Ji Ming, "Noise compensation for speech recognition with arbitrary additive noise," IEEE Transactions on Speech and Audio Processing, vol. 14, pp. 833-844, 2006.
[26]  Ji Ming, J. Lin and F. J. Smith, "A posterior union model with applications to robust speech and speaker recognition," EURASIP Journal on Applied Signal Processing, vol. 2006, Article ID 75390, Pages 1-12.
[27]  Ji Ming, T. J. Hazen and J. R. Glass, "Speaker verification over handheld devices with realistic noisy speech data," International Conference on Acoustics, Speech, and Signal Processing (ICASSP'2006), pp. 637-640, Toulouse, France, May 2006.
[28]  Ji Ming, T. J. Hazen and J. R. Glass, "A comparative study of methods for handheld speaker verification in realistic noisy conditions," IEEE Odyssey 2006-The Speaker and Language Recognition Workshop, Puerto Rico, Jun 2006.
[29]  J. McAuley, Ji Ming, D. Stewart and P. Hanna, "Subband correlation and robust speech recognition," IEEE Transactions on Speech and Audio Processing, vol. 13, pp. 956-964, 2005.
[30]  Ji Ming, D. Stewart and S. Vaseghi, "Speaker identification in unknown noisy conditions-a universal compensation approach," International Conference on Acoustics, Speech, and Signal Processing (ICASSP'2005), pp. 617-620, Philadelphia, PA, March 2005.
[31]  J. McAuley, Ji Ming, P. Corr, "Speaker verification in noisy conditions using correlated subband features," Interspeech-Eurospeech'2005, pp. 2001-2004, Lisbon, Portugal, Sept 2005.
[32]  Elvira I. Sicilia-Garcia, Ji Ming, F. J. Smith, "A posteriori multiple word-domain language model," Interspeech-Eurospeech'2005, pp. 1285-1288, Lisbon, Portugal, Sept 2005.
[33]  R. Seymour, Ji Ming, D. Stewart, "A new posterior based audio-visual integration method for robust speech recognition," Interspeech-Eurospeech'2005, pp. 1229-1232, Lisbon, Portugal, Sept 2005.
[34]  Ji Ming, "Noise compensation for speech recognition with arbitrary additive noise," IEE Electronics Letters, vol. 40, pp. 206-207, 2004.
[35]  Ji Ming and B. Hou, "Evaluation of universal compensation on Aurora 2 and 3 and beyond," International Conference on Spoken Language Processing (ICSLP'2004), pp. 97-100, Jeju Island, Korea, Oct 2004.
[36]  C. Conn, Ji Ming and P. Hanna, "Robust keyword spotting using a multi-stream approach," International Conference on Speech and Computer (SPECOM'04), pp. 260-267, St. Petersburg, Sept 2004.
[37]  Ji Ming, "Universal compensation-an approach to noisy speech recognition assuming no knowledge of noise," International Conference on Acoustics, Speech, and Signal Processing (ICASSP'2004), pp. I.961-I.964, Montreal, May 2004.
[38]  J. McAuley, Ji Ming, P. Hanna and D. Stewart, "Modeling subband correlation for noise-robust speech recognition," International Conference on Acoustics, Speech, and Signal Processing (ICASSP'2004), pp. I.1017-I.1020, Montreal, May 2004.
[39]  L. Q. Ha, E. Sicilia, Ji Ming and F. J. Smith, "Extension of Zipf's law to word and character n-grams for English and Chinese," International Journal of Computational Linguistics and Chinese Language Processing, vol. 8, pp. 77-102, 2003.
[40]  Ji Ming and J. Lin, "A posterior union model for robust speech recognition," IEE Electronics Letters, vol. 39, pp. 162-163, 2003.
[41]  Ji Ming, D. Stewart, P. Hanna, P. Corr, F. J. Smith and S. Vaseghi, "Robust speaker identification using posterior union models," European Conference on Speech Communication and Technology (Eurospeech'2003), pp. 2645-2648, Geneva, Sept 2003.
[42]  R. Ventura-Miravet, F. Murtagh and Ji Ming, "Pattern recognition of musical instruments using hidden Markov models," Stockholm Music Acoustics Conference (SMAC'2003), pp. 667-670, Stockholm, Aug 2003. (ISBN 91-7283-559-1)
[43]  Ji Ming and F. J. Smith, "A posterior union model for improved robust speech recognition in nonstationary noise," International Conference on Acoustics, Speech, and Signal Processing (ICASSP'2003), pp. 420-423, Hong Kong, Apr 2003.
[44]  Ji Ming, P. Jancovic and F. J. Smith, "Robust speech recognition using probabilistic union models," IEEE Transactions on Speech and Audio Processing, vol. 10, pp. 403-414, 2002.
[45]  D. Stewart, Ji Ming, P. Hanna and F. J. Smith, "A state tying approach to building syllable HMMs," International Conference on Spoken Language Processing (ICSLP'2002), pp. 2649-2652, Denver, Colorado, Sept 2002.
[46]  E. Sicilia, Ji Ming and F. J. Smith, "Individual word language models and the frequency approach," International Conference on Spoken Language Processing (ICSLP'2002), pp. 897-900, Denver, Colorado, Sept 2002.
[47]  L. Q. Ha, E. Sicilia, Ji Ming and F. J. Smith, "Extension of Zipf's law to words and phrases," International Conference on Computational Linguistics (COLING'2002), pp. 315-320, Taipei, Taiwan, Aug 2002.
[48]  P. Jancovic and Ji Ming, "Combining the union model and missing feature method to improve noise robustness in ASR," International Conference on Acoustics, Speech, and Signal Processing (ICASSP'2002), pp. 69-72, Orlando, FL, May 2002.
[49]  P. Jancovic and Ji Ming, "A probabilistic union model with automatic order selection for noisy speech recognition," Journal of Acoustic Society of America, vol. 110, No. 3, pp. 1641-1648, 2001.
[50]  Ji Ming and F. J. Smith, "Union: a model for partial temporal corruption of speech," Computer Speech and Language, vol. 15, pp. 217-231, 2001.
[51]  Ji Ming and F. J. Smith, "Union: a new approach for combining sub-band observations for noisy speech recognition," Speech Communication, Special Issue on Robust Speech Recognition, vol. 34, No. 1-2, pp. 41-55, 2001.
[52]  Ji Ming, "An improved union model for continuous speech recognition with partial duration corruption," IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 25-28, Trento, Italy, Dec 2001.
[53]  Ji Ming, P. Jancovic, P. Hanna and D. Stewart, "Modeling the mixtures of known noise and unknown unexpected noise for robust speech recognition," European Conference on Speech Communication and Technology (Eurospeech'2001), pp. 579-582, Aalborg, Denmark, Sept 2001.
[54]  P. Jancovic and Ji Ming, "A multi-band approach based on the probabilistic union model and frequency-filtering features for robust speech recognition," European Conference on Speech Communication and Technology (Eurospeech'2001), pp. 1111-1114, Aalborg, Denmark, Sept 2001.
[55]  E. Sicilia, Ji Ming and F. J. Smith, "Triggering individual word domains in n-gram language models," European Conference on Speech Communication and Technology (Eurospeech'2001), pp. 701-704, Aalborg, Denmark, Sept 2001.
[56]  Ji Ming, P. Jancovic and F. J. Smith, "Robust feature selection using probabilistic union models," International Conference on Spoken Language Processing (ICSLP'2000), pp. 546-549, Beijing, Oct 2000.
[57]  P. Hanna, D. Stewart and Ji Ming, "Improved lexicon formation through removal of co-articulation and acoustic recognition errors," International Conference on Spoken Language Processing (ICSLP'2000), pp. 50-53, Beijing, Oct 2000.
[58]  E. Sicilia, Ji Ming, and F. J. Smith, "A dynamic language model for each significant word," 4th Conference of the International Quantitative Linguistics Association (Qualico'2000), pp. 66-67, Prague, Aug 2000.
[59]  E. Sicilia, Ji Ming, and F. J. Smith, "A dynamic language model based on individual word domains," 18th International Conference on Computational Linguistics, Saarbrucken, Germany, Jul-Aug 2000.
[60]  P. Corr, D. Stewart, P. Hanna, Ji Ming and F. J. Smith, "Discrete Chebyshev transformation-a natural modification of the DCT," 15th International Conference on Pattern Recognition, pp. 1154-1157, Barcelona, Sept 2000.
[61]  P. Jancovic, Ji Ming, P. Hanna, D. Stewart and F. J. Smith, "Combining multi-band and frequency-filtering techniques for speech recognition in noisy environments," 3rd International Workshop on Text, Speech and Dialogue, Lecture Notes in Artificial Intelligence, Springer, pp. 265-270, Brno, Czech Republic, Sept 2000.
[62]  Ji Ming, P. Hanna, D. Stewart and F. J. Smith, "Union: a model for speech recognition subjected to partial and temporal corruption with unknown, time-varying noise statistics," European Signal Processing Conference (EUSIPCO'2000), Tampere, Finland, Sept 2000.
[63]  Ji Ming and F. J. Smith, "A probabilistic union model for sub-band based robust speech recognition," International Conference on Acoustics, Speech, and Signal Processing (ICASSP'2000), pp. 1787-1790, Istanbul, Jun 2000.
[64]  Ji Ming, P. O'Boyle, M. Owens and F. J. Smith, "A Bayesian approach for building triphone models for continuous speech recognition," IEEE Transactions on Speech and Audio Processing, vol. 7, pp. 678-684, 1999.
[65]  Ji Ming and F. J. Smith, "A Bayesian triphone model," Computer Speech and Language, vol. 13, pp. 195-206, 1999.
[66]  P. Hanna, Ji Ming and F. J. Smith, "Interframe dependence arising from preceding and succeeding frames-application to speech recognition," Speech Communication, vol. 28, pp. 301-312, 1999.
[67]  P. O'Boyle, Ji Ming, M. Ownes and F. J. Smith, "Adaptive parameter training in an interpolated n-gram language model," Journal of Quantitative Linguistics, vol. 6, pp. 10-13, 1999.
[68]  Ji Ming, D. Stewart, P. Hanna and F. J. Smith, "A probabilistic union model for partial and temporal corruption of speech," IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 43-46, Keystone, Colorado, Dec 1999.
[69]  P. Donnelly, F. J. Smith, E. Sicilia and Ji Ming, "Language modeling with hierarchical domains," European Conference on Speech Communication and Technology (Eurospeech'99), pp. 1575-1578, Budapest, Sept 1999.
[70]  P. Hanna, D. Stewart and Ji Ming, "The application of an improved DP match for automatic lexicon generation," European Conference on Speech Communication and Technology (Eurospeech'99), pp. 475-478, Budapest, Sept 1999.
[71]  M. Owens, A. Kruger, F. J. Smith and Ji Ming, "A missing-word test comparison of human and statistical language model performance," European Conference on Speech Communication and Technology (Eurospeech'99), pp. 145-148, Budapest, Sept 1999.
[72]  D. Stewart, P. Hanna, Ji Ming and F. J. Smith, "An improved method of automatically generating alternative lexicon pronunciations," International Congress of Phonetic Sciences (ICPhS'99), pp. 1713-1716, San Francisco, Aug 1999.
[73]  P. Hanna, D. Stewart, Ji Ming and F. J. Smith, "An improved DP match for automatic lexicon generation," International Congress of Phonetic Sciences (ICPhS'99), pp. 1717-1720, San Francisco, Aug 1999.
[74]  F. J. Smith, and Ji Ming, "Modeling correlation of an ensemble," IEEE Signal Processing Workshop on Higher-Order Statistics, pp. 349-352, Ceasarea, Israel, Jun 1999.
[75]  Ji Ming and F. J. Smith, "Union: a new approach for combining sub-band observations for noisy speech recognition," International Workshop on Robust Methods for Speech Recognition in Adverse Conditions, pp. 175-178, Tampere, Finland, May 1999.
[76]  Ji Ming, P. Hanna, D. Stewart, M. Owens and F. J. Smith, "Improving speech recognition performance by using multi-model approaches," International Conference on Acoustics, Speech, and Signal Processing (ICASSP'99), pp. 161-164, Phoenix, USA, Mar 1999.
[77]  P. Hanna, N. Harte, Ji Ming, S. Vaseghi and F. J. Smith, "Varying the feature vectors of the interframe dependent HMM for speech recognition," IEE Electronics Letters, vol. 34, pp. 858-859, 1998.
[78]  Ji Ming, P. Hanna, D. Stewart, S, Vaseghi and F. J. Smith, "Capturing discriminative information using multiple modeling techniques," International Conference on Spoken Language Processing (ICSLP'98), pp. 2791-2794, Sydney, Dec. 1998.
[79]  A. Kruger, M. Owens, Ji Ming and Smith, F.J. "Insight into human use of context information-a study using missing-word tests," International Conference on Speech and Computer (SPECOM'98), pp. 249-252, St. Petersburg, Oct 1998.
[80]  Ji Ming, M. Owens and F. J. Smith, "A Bayesian triphone model with parameter tying," European Signal Processing Conference (EUSIPCO'98), pp. 351-354, Rhodes, Greece, Sept 1998.
[81]  D. Stewart, Ji Ming and F. J. Smith, "Automatic syllabification with applications to continuous speech recognition," International Phonetic Sciences Conference, pp. 109-113, Washington, Jun 1998.
[82]  Ji Ming and F. J. Smith, "Improved phone recognition using Bayesian triphone models," International Conference on Acoustics, Speech, and Signal Processing (ICASSP'98), pp. 409-412, Seattle, May 1998.
[83]  D. Stewart and Ji Ming, "Using automatic syllabification to count syllable and demi-syllable frequencies," 1998 British Association of Academic Phoneticians Colloquium, Belfast, Apr 1998.
[84]  M. Owens, P. O'Boyle, J. McMahon, Ji Ming and F. J. Smith, "A comparison of human and statistical language model performance using missing-word test," Language and Speech, vol. 40, pp. 377-389, 1997.
[85]  P. Hanna, Ji Ming and F. J. Smith, "Modeling interframe dependence with preceding and succeeding frames," European Conference on Speech Communication and Technology (Eurospeech'97), pp. 1167-1170, Rhodes, Greece, Sept 1997.
[86]  P. O'Boyle, Ji Ming and F. J. Smith, "From phone identification to phone clustering using mutual information," European Conference on Speech Communication and Technology (Eurospeech'97), pp. 2391-2394, Rhodes, Greece, Sept 1997.
[87]  P. O'Boyle, Ji Ming and F. J. Smith, "Adaptive parameter training in an interpolated n-gram language model," International Conference on Quantitative Linguistics, pp. 177-181, Helsinki, Aug 1997.
[88]  Ji Ming and F. J. Smith, "Modelling of the interframme dependence in an HMM using conditional Gaussian mixtures," Computer Speech and Language, vol. 10, pp. 229-247, 1996.
[89]  Ji Ming and F. J. Smith, "Stochastic correlation model for speech recognition," IEE Electronics Letters, vol. 32, pp. 970-971, 1996.
[90]  Ji Ming, P. O'Boyle, J. McMahon and F. J. Smith, "Speech recognition using a strong correlation assumption for the instantaneous spectra," International Conference on Spoken Language Processing (ICSLP'96), pp. 343-346, Philadelphia, Oct 1996.
[91]  F. J. Owens, Ji Ming, S. Murphy and T. Maguire, "Algorithms for compressing ultrasonic images and audio Doppler ultrasound at very low rate," First International Conference on Simulation and Modeling in Bioengineering (BIOSIM'96), pp. 249-258, Merida, Venezuela, Oct 1996.
[92]  Ji Ming and F. J. Owens, "Data compression of moving medical ultrasonic images for transmission over ISDN," Irish DSP and Control Colloquium (IDSPCC'96), Dublin, Jun 1996.
[93]  P. O'Boyle, Ji Ming, J. McMahon and F. J. Smith, "Improving n-gram models by incorporating enhanced distributions," International Conference on Acoustics, Speech, and Signal Processing (ICASSP'96), pp. 168-171, Atlanta, May 1996.
[94]  F. J. Smith and Ji Ming, "An improved HMM for robust speech recognition," International Conference on Signal Processing Applications & Technology (ICSPAT'95), pp. 2034-2037, Boston, Oct 1995.
[95]  Ji Ming, P. O'Boyle and F. J. Smith, "An HMM with optimized segment-dependent observations for speech recognition," European Conference on Speech Communication and Technology (Eurospeech'95), pp. 1475-1478, Madrid, Sept 1995.
[96]  P. O'Boyle and Ji Ming, "Markov models of speech and language," Irish DSP and Control Colloquium (IDSPCC'95), pp. 205-212, Belfast, Jun 1995.
[97]  F. J. Smith, Ji Ming, P. O'Boyle and A. Irvine, "A hidden Markov model with optimized interframe dependence," International Conference on Acoustics, Speech, and Signal Processing (ICASSP'95), pp. 209-212, Detroit, May 1995.
[98]  Ji Ming and F. J. Smith, "Isolated word recognition using inter-frame dependent hidden Markov models," IEEE Signal Processing Letters, vol. 1, pp. 188-190, 1994.
[99]  Ji Ming and F. J. Smith, "Inter-frame dependent hidden Markov models for speech recognition," IEE Electronics Letters, vol. 30, pp. 188-189, 1994.
[100]  Ji Ming, A. D. Irvine and F. J. Smith, "On the separability of speech signals," European Signal Processing Conference (EUSIPCO'94), pp.1633-1636, Edinburgh, Sept 1994.
[101]  Ji Ming and H. Chen, "A neural network approach to robust phoneme recognition," European Signal Processing Conference (EUSIPCO'92), pp.355-358, Brussels, Aug 1992.
[102]  Ji Ming, H. Chen and Z. Shen, "Robust shape recognition using space perturbation neural networks," Applications of Artificial Neural Networks III, Pts. 1 and 2, Ch. 111, pp.283-291, 1992.
[103]  Ji Ming and Z. Shen, "A novel neural network for object recognition with blurred shapes," IEEE International Symposium on Circuits and Systems (ISCAS'92), pp. 2901-2904, San Diego, May 1992.
[104]  Ji Ming, H. Chen and Z. Shen, "A space-perturbance/time-delay neural network for speech recognition," IEEE International Workshop on Neural Networks for Signal Processing, pp. 385-394, Princeton, Sept. 1991.
[105]  Ji Ming, Y. Ke and M. Lin, "The statistical information formulation for noisy speech recognition," International Conference on Signal Processing, Beijing, Oct 1990.
[106]  Ji Ming, "The statistical information formulation for noisy speech recognition," 10th International Conference on Pattern Recognition, pp.236-239, Atlantic City, Jun 1990.
[107]  Ji Ming and Z. Shen, "Noisy speech processing-a unified information approach," International Conference on Computer Processing of Chinese and Oriental Languages, Changsha, China, Nov 1989.
[108]  Ji Ming, Y. Ke and M. Lin, "On the optimality of methods for speech and noisy speech recognition," International Workshop on Information Theory, Beijing, Jul 1988.