Conversational Biometrics Group - Ran Zilca

Ran D. Zilca

Conversational Biometrics Group
Human Language Technologies
IBM Research

Ran Zilca


Ran D. Zilca received the B.S. degree (honors) in electrical engineering from Ben Gurion University, Israel, in 1993, and the M.S. degree in electrical engineering from Tel Aviv University, Israel, in 1997.
From 1993 to 1999 he was with the Israel Defense Forces (IDF), where he managed different research and development groups working on interdisciplinary projects involving signal processing, pattern recognition, and data mining.
From 1999 to 2001 he was a research scientist with the R&D division of Amdocs, Israel, where he conducted research in text independent speaker recognition for landline and cellular environments, focusing on computationally efficient large population open-set speaker identification. During this time, he also managed a group of developers working on a robust voice portal for cellular providers.
In 2001 he joined the Human Language Technology Department at the IBM T. J. Watson Center in Yorktown Heights NY, where he is conducting research in robust and efficient speaker recognition and interaction models for secure remote user authentication.
His current research interests include statistical pattern recognition, statistical modeling, and robust speaker verification and identification. Ran is a senior member of IEEE.


  • R. D. Zilca, B. Kingsbury, J. Navratil, G. Ramaswamy, “Pseudo Pitch Synchronous Analysis of Speech,” to appear in IEEE tran. Speech and audio proc.
  • J. H. Nealand, J. W. Pelecanos, R. D. Zilca, and G. N. Ramaswamy, "A Study of the Relative Importance of Temporal Characteristics In Text-Dependent and Text-Constrained Speaker Verification," ICASSP 2005.
  • J. Navratil, G. N. Ramaswamy, R. D Zilca, “Statistical Model Migration in Speaker Recognition,” ICSLP 2004.
  • R. D. Zilca, J. W. Pelecanos, U. V. Chaudhari, and G. N. Ramaswamy, "Real Time Robust Speech Detection for Text Independent Speaker Recognition," Odyssey speaker and language recognition workshop 6/2004.
  • J. Navratil, G. N. Ramaswamy, and R. D. Zilca, "Statistical Model Migration in Speaker Recognition," ICSLP 2004.
  • R. D. Zilca, J. Navratil, and G. N. Ramaswamy, "Syncpitch: A Pseudo Pitch Synchronous Algorithm for Speker Recognition," EUROSPEECH 2003.
  • G. N. Ramaswamy, R. D. Zilca, and O. Alecksandrovich, "A Programmable Policy Manager for Conversational Biometrics," EUROSPEECH 2003.
  • R. D. Zilca, J. Navratil, and G. N. Ramaswamy, "Depitch and the Role of Fundamental Frequency in Speaker Recognition," ICASSP 2003.
  • G. N. Ramaswamy, J. Navratil, U. V. Chadhari, and R. D. Zilca, "The IBM System for the NIST 2002 Cellular Speaker Verification Evaluation," ICASSP 2003.
  • R. D. Zilca, "Text Independent Speaker Verification using Utterance Level Scoring and Covariance Modeling," IEEE tran. Speech and audio proc., September 2002.
  • R. D. Zilca, U. Chaudhari, and G. Ramaswamy, "The Sphericity Measure for Cellular Speaker Verification," ICASSP 2002.
  • U. Chaudhari, J. Navratil, G. Ramaswamy, and R. Zilca, "Future Speaker Recognition Systems - Challenges and Solutions", AutoID-2002, Tarrytown, NY March 2002.
  • R. D. Zilca, "Using Second Order Statistics for Text Independent Speaker Verification", Odyssey 2001 Speaker Recognition Workshop, Crete-Greece, June 2001.
  • R. D. Zilca, "Text Independent Speaker Verification using Covariance Modeling", IEEE Signal Processing Letters, April 2001.
  • R. D. Zilca and Y. Bistritz, "Distance Based Gaussian Mixture Model for Speaker Recognition", ICSLP-2000, Beijing 10/2000.
  • R. D. Zilca and Y. Bistritz, "Feature Concatenation for Speaker Identification", European Signal Processing Conference, Tampere, Finland, 9/2000.
  • R. D. Zilca and Y. Bistritz, "Text Independent Speaker Identification using LSP Codebook Speaker Models and Linear Discriminant Functions", Eurospeech 9/99, Budapest.
  • S. Grinberg, H. Guterman, R. Sharon, and R. Zilca "Translation, rotation and scale invariant image classifier using an artificial neural network", Israeli Information Processing Conference, 12/93, Israel.


Issued Patents:
  • US6772119 Computationally Efficient Method and Apparatus for Speaker Recognition.
Pending Patents:
List available upon request.

Contact Information:
Ran Zilca
Human Language Technologies
Thomas J. Watson Research Center
Rt. 134, Room 18-104
Yorktown Heights, NY 10598 U.S.A.
Tel.: (914) 945-3013
Fax.: (914) 945-4490
E-mail: Contact