Upendra V. Chaudhari

Research Staff Member, Conversational Biometrics Group
Human Language Technologies
IBM Research

Biography:

Upendra V. Chaudhari received the S.B.'91, S.M.'93, and Ph.D.'97 degrees from the Massachusetts Institute of Technology, where the main focus of his research was in the field of statistical signal processing and non-orthogonal signal expansions. Dr. Chaudhari became a Post Doctoral Associate at MIT after finishing his Ph.D and continued work on signal expansions, particularly for speech. While at MIT, Dr. Chaudhari also worked on computational complexity, multi-access communication theory, and information retrieval. Later, he moved to the Human Language Technologies Group at the IBM T. J. Watson Research Center where he is a Research Staff Member. His work centers on statistical modeling and signal processing, with applications in speaker modeling and recognition.

Professional Preparation
Ph.D. '97	Massachusetts Institute of Technology 
          	Electrical Engineering and Computer Science 

S.M. '93       Massachusetts Institute of Technology 
               Electrical Engineering and Computer Science 

S.B. '91       Massachusetts Institute of Technology 
               Electrical Engineering and Computer Science 

Postdoctoral Advisor: Prof. S.K. Mitter (MIT) 

Thesis Advisors: Prof. S.K. Mitter (MIT), 
                 Prof. A. S. Willsky (MIT), 
                 Prof. K. N. Stevens (MIT)
Appointments

1998-Present Research Staff Member, I.B.M. Thomas J. Watson Research Center
1997-1998 Postdoctoral Associate, I.B.M. Thomas J. Watson Research Center
1997 Postdoctoral Associate, Massachusetts Institute of Technology
Summer 1996  I.B.M. Thomas J. Watson Research Center
Summer 1995  Inteq Corp.
Summer 1994  B.B.N.
1989-1991  Undergraduate Researcher, Spoken Language Systems Group (MIT)
Summers 1986-88 NASA Ames Research Center, Human Factors Division

Selected Publications

• U.V. Chaudhari, J. Navratil, S.H. Maes ``Multi-Grained modeling with pattern specific maximum likelihood transformations for text-independent speaker recognition," to appear (Jan-Feb) in IEEE Trans. Speech and Audio Processing, 2003.
• U.V. Chaudhari, G.N. Ramaswamy, G. Potamianos, C. Neti, ``Audio-visual speaker recognition using time-varying stream reliability prediction," ICASSP-2003, Hong Kong, April, 2003.
• G.N. Ramaswamy, J. Navratil, U.V. Chaudhari, R.D. Zilca, ``The IBM system for the NIST 2002 cellular speaker verification evaluation," Submitted to ICASSP-2003, Hong Kong, April, 2003.
• U.V. Chaudhari, J. Navratil, G.N. Ramaswamy, R.D. Zilca ``Future speaker recognition systems: Challenges and solutions," Proc. of AUTOID-2002, Tarrytown, NY, March 2002.
• B. Xiang, U.V. Chaudhari, J. Navratil, G.N. Ramaswamy, R.A. Gopinath, ``Short-time Gaussianization for robust speaker verification," In Proc. of the ICASSP-2002, Orlando, Florida, May 2002.
• R.D. Zilca, U.V. Chaudhari, G.N. Ramaswamy, ``The sphericity measure for cellular speaker verification," Proc. of the ICASSP-2002, Orlando, Florida, May 2002.
• U.V. Chaudhari, J. Navratil, G.N. Ramaswamy, S.H. Maes, ``Very large population text-independent speaker identification using transformation enhanced multi-grained models," ICASSP 2001, Salt Lake City, Utah, May 2001.
• S.H. Maes, J. Navratil, U.V. Chaudhari, ``Conversational Speech Biometrics," Chapter in "E-Commerce Agents. Marketplace Solutions, Security Issues, ans Supply Demand," LNAI 2033, Springer Verlag, 2001.
• J. Navratil, U.V. Chaudhari, G.N. Ramaswamy, ``Speaker verification using target and background dependent linear transforms and multi-system fusion," Proc. of EUROSPEECH-01, Aalborg, Denmark, September 2001.
• U.V. Chaudhari, J. Navratil, S.H. Maes, ``Transformation enhanced multi-grained modeling for text-independent speaker recognition," ICSLP 2000, Beijing, October 2000.
• J. Navratil, U.V. Chaudhari, S.H. Maes, ``A speech biometric system with multi-grained speaker modeling," KONVENS 2000, Ilmenau, Germany, October 2000.
• Homayoon S.M. Beigi, Stephane H. Maes, Upendra V. Chaudhari and Jeffrey S. Sorensen, ``A Hierarchical Approach to Large-Scale Speaker Recognition,'' EUROSPEECH'99, Budapest, Hungary, September 5-9, 1999, Vol. 5, pp. 2203-2206.
• Upendra V. Chaudhari, Homayoon S.M. Beigi, Stephane H. Maes, and Jeffrey S. Sorensen, ``Multi-Environment Speaker Verification,'' AUTOID'99, New Jersey, 1999.
• Homayoon S. M. Beigi, Stephane H. Maes, Upendra V. Chaudhari, and Jeffrey S. Sorensen, ``IBM Model-Based and Frame-By-Frame Speaker Recognition,'' Speaker Recognition and its Commercial and Forensic Appications, Avignon, France, Apr. 20-23, 1998.
  
  
  

  Contact Information:
  Upendra Chaudhari
  Human Language Technologies
  Thomas J. Watson Research Center
  Rt. 134, Room
  Yorktown Heights, NY 10598 U.S.A.
  Tel.: (914) 945-3098
  Fax.: (914) 945-4490
  E-mail: Contact