Publications in Speech Recognition and Machine Learning

• Anumanchipalli, G., Ravishankar, M., and Reddy, R.,
  Improving Pronunciation Inference Using N-Best List, Acoustics and Orthography
  To appear in Proc. of ICASSP, Honolulu, Hawaii, Apr 16-20, 2006. pdf.

• Prahallad, K., Black, A., and Ravishankar, M.,
  Sub-phonetic Modeling for Capturing Pronunciation Variations for Conversational Speech Synthesis
  Proc. of ICASSP, Toulouse, May 16-19, 2006. pdf.

• Huggins-Daines, D. et al,
  PocketSphinx: A Free, Real-Time Continuous Speech Recognition System for Hand-Held Devices
  Proc. of ICASSP, Toulouse, May 16-19, 2006. pdf.

• Chan, A., Ravishankar, M., and Rudnicky, A.,
  On Improvements to CI-Based GMM Selection
  Proc. of Interspeech Conference, Lisbon, Sep. 5-8, 2005. pdf.

• Chan, A., Sherwani, J., Ravishankar, M. and Rudnicky, A.,
  Four-Level Categorization Scheme of Fast GMM Computation Techniques in Large Vocabulary Continuous Speech Recognition Systems
  Intl. Conf. on Speech and Language Processing, Jeju, Korea, Oct. 5-8, 2004. postscript.

• Tomasic, A. et al,
  Learning to Navigate Web Forms
  Workshop on Information Integration on the Web (IIWEB 2004), Toronto, Canada, 2004.

• Ravishankar, M., Singh, R., Raj, B. and Stern, R.,
  The 1999 CMU 10x real time broadcast news transcription system
  Proc. DARPA Workshop on Automatic Transcription of Broadcast News, Washington DC, May 2000. pdf.

• Bansal, D. and Ravishankar, M.,
  New Features for Confidence Annotation.
  Proceedings of ICSLP, Nov-Dec 1998. postscript.

• Ravishankar, M., Bisiani, R. and Thayer, E.,
  Sub-Vector Clustering to Improve Memory and Speed Performance of Acoustic Likelihood Computation.
  Proceedings of Eurospeech, Sep 1997, vol 1, pp 151-154. postscript.

• Ravishankar, M., Eskenazi, M.,
  Automatic Generation of Context-Dependent Pronunciations.
  Proceedings of Eurospeech, Sep 1997, vol 5, pp 2467-2470. postscript.

• Ravishankar, M.,
  Some Results on Search Complexity vs Accuracy.
  DARPA Speech Recognition Workshop, Feb 1997. postscript, html.

• Ravishankar, M.,
  Efficient Algorithms for Speech Recognition.
  Ph.D Thesis, Carnegie Mellon University, May 1996, Tech Report. CMU-CS-96-143. postscript, pdf.

• Placeway , P. et al,
  The 1996 Hub-4 Sphinx-3 System. Proc. Spoken Lang. Tech. Wkshp., Feb 1997.

• Chase, L. et al,
  Improvements in Language, Lexical, and Phonetic Modeling in Sphinx-II.
  Proc. Spoken Lang. Tech. Wkshp., Jan 1995, pp 60-65.

• Hwang, M. et al,
  Improving Speech Recognition Performance via Phone-Dependent VQ Codebooks and Adaptive Language Models in Sphinx-II.
  Proceedings of ICASSP, Apr 1994, pp I-549 - I-552.

• Rosenfeld, R. et al,
  Improved Acoustic and Adaptive Language Models for Continuous Speech Recognition.
  Proc. Spoken Lang. Tech. Wkshp., Mar 1994, pp 106-109.

• Ravishankar, M.,
  Parallel Implementation of Fast Beam Search for Speaker-Independent Continuous Speech Recognition.
  Technical Report submitted to Indian Institute of Science, Bangalore, July 1993. postscript.