Office:   CSE 3014

Tel:        (416) 736-2100 x33346

Fax:       (416) 736-5872

Email:     hj AT cs DOT yorku DOT ca
 

HUI  JIANG

Associate Professor, Department of Computer Science and Engineering,

York University, Toronto, M3J 1P3, CANADA

 
 
        

 

I am currently working on various topics related to speech, language and bioinformatics. We are located in the Signal Processing and Communication Lab (CSE2052) at York University.  If you are interested in doing research with me, please email me at the above address.

 

Research Interests

 

  • Machine Learning / Statistical Pattern Classification
  • Speech and Audio Processing (recognition, enhancement, 3-D audio, voice conversion, etc)
  • Statistical Language Processing (text categorization, etc)
  • Bioinformatics (gene finding, protein function prediction, etc)
  • Multimedia Information Retrieval

 

Recent Representative Publication:

( Check here for my full publication list. )

 

[1] H.Jiang, X. Li and C.-J. Liu, ``Large Margin Hidden Markov Models for Speech Recognition,’’ IEEE Trans. On Audio, Speech and Language Processing (formerly IEEE Trans. on Speech and Audio Processing),  pp.1584-1595, Vol. 14, No. 5, September 2006.

[2] H. Jiang, F. Soong and C.-H. Lee, ``A Dynamic In-search Data Selection Method with its Applications to Acoustic Modeling and Utterance Verification,” IEEE Trans. on Speech and Audio Processing,  pp.945-955, Vol. 13, No.5, September 2005.

[3] H. Jiang, ``Confidence Measures for Speech Recognition: A Survey", Speech Communication, Vol. 45,  No. 4,  pp. 455-470, Apr. 2005.

[4] H. Jiang, C.-H. Lee, ``A new approach to utterance verification based on neighborhood information in model space,'' IEEE Trans. on Speech and Audio Processing, pp.425-434, Vol. 11, No.5, September 2003.

[5] H. Jiang and L. Deng, ``A Bayesian approach to the verification problem: -- applications to speaker verification,'' IEEE Trans. on Speech and Audio Processing, pp.874-884, Vol. 9, No.8,  November 2001.

[6] H. Jiang, K. Hirose and Q. Huo, ``Robust speech recognition based on Bayesian prediction approach'', IEEE Trans. on Speech and Audio Processing,  pp. 426-440, Vol. 7, No.4, July 1999. 

 

(Check here for My Full Publication List)

 

Recent Invited Talks

 

  • Februray 2006,  “Large Margin HMMs for Speech Recognition,” Microsoft Research, Redmond, Washington, USA.  (slides, Video)
  • January 2006,  “Model-based Speech Processing: Recognition, Enhancement and Separation,” Zarlink Semiconductor Inc., Ottawa, Ontario.  (slides)
  • Februrary 2005, “Large-Margin HMM Estimation for Speech Recognition,” IBM Waston Research Center, Yorktown Heights, New York. (slides)
  • April 2004, “An In-search Data Selection Algorithm and its Applications,” Microsoft Research Asia, Beijing, China. (slides)
  • November 2003, “Confidence Measures: How Much We can Trust Our Speech Recognizers,” University of Toronto, Toronto, Ontario. (slides)

 

Supervision of Students

   

·        Postdoctoral Fellows

·        Ph.D. Students

·        Master Students

·        Undergraduate Students

 

Teaching

   

     All Courses taught in York University since 2002.

 

(Last update on March 28, 2006)