PUBLICATIONS

  1. Probabilistic deduction of symbol mappings for extension of lexicons, Rita Singh, Evandro Gouvea, Bhiksha Raj Interspeech 2007, Antwerp, Blegium, August 2007 -- submitted.pdf

  2. Bandwidth expansion with a polya urn model, Bhiksha Raj, Rita Singh, Madhusudhana Shashanka, Paris Smaragdis, ICASSP, Honolulu, Hawaii, April 2007.pdf

  3. Separating a singing voice from background music for song personalization, Bhiksha Raj, Paris Smaragdis, Madhusudhana Shashanka, Rita Singh, Frontiers of Research in Speech and Music, Mysore, India, January 2007.pdf

  4. Voice driven applications in non-stationary and chaotic environments, C. Kwan, X. Li, D. Lao, Y. Deng, B. Raj, R. Singh, and R. Stern, Int. J. Signal Processing, October 2005.

  5. Recognizing speech from simultaneous speakers, Bhiksha Raj, Rita Singh, Paris Smaragdis, Proc. Interspeech 2005, Lisbon, Portugal, September 2005.

  6. Feature compensation with secondary sensor measurements for robust speech recognition, Bhiksha Raj, Rita Singh, Proc. Eusipco 2005, Antalya, Turkey, August 2005.

  7. Maximum-likelihood adaptation of semi-continuous HMMs by latent variable decomposition of state distributions, Antoine Raux and Rita Singh, ICSLP, Korea, 2004. pdf

  8. Probabilistic Markovian models for fractal data sequences, Rita Singh , 1st Asia-Oceania Geosciences Society Annual Meeting (AOGS 2004), Singapore, 5-9 July, 2004. (Invited paper) pdf

  9. Classification in likelihood spaces , Rita Singh, Bhiksha Raj, Technometrics, Vol. 45, No. 3, 2004. pdf

  10. On tracking noise with linear dynamical system models, Bhiksha Raj, Rita Singh, Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP 2004), Montreal, Canada, May 17-21, 2004. ( to appear) pdf

  11. Classification with free energy at raised temperatures, Rita Singh, Manfred K. Warmuth, Bhiksha Raj and Paul Lamere, 8th European Conf. on Speech Communication and Technology (EUROSPEECH 2003) , Geneva, Switzerland, September 1-4, 2003. pdf

  12. Design of the CMU Sphinx-4 decoder, Paul Lamere, Philip Kwok, William Walker, Evandro Gouvea, Rita Singh, Bhiksha Raj, Peter Wolf , 8th European Conf. on Speech Communication and Technology (EUROSPEECH 2003) , Geneva, Switzerland, September 1-4, 2003. pdf

  13. Tracking noise via dynamical systems with a continuum of states, Rita Singh and Bhiksha Raj, Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP 2003), HongKong, April 6-10, 2003. pdf

  14. Classifier-based non-linear projection for adaptive endpointing of continuous speech, Bhiksha Raj and Rita Singh, Computer Speech and Language, Vol. 17, Issue 1, pp.5-26, January 2003. pdf : uncorrected proof

  15. Rapid deployment of speech-to-speech translation systems, Alan Black, Ralf Brown, Robert Frederking, Kevin Lenzo, John Moody, Alexander Rudnicky, Rita Singh, Eric Steinbrecher, Proc. 7th International Conference on Spoken Language Processing (ICSLP 2002), Denver, Colorado, Sept. 16-20, 2002.

  16. Combining search spaces of heterogeneous recognizers for improved speech recognition, Xiang Li, Rita Singh and Richard Stern, Proc. 7th International Conference on Spoken Language Processing (ICSLP 2002), Denver, Colorado, Sept. 16-20, 2002. pdf

  17. TONGUES: Rapid development of a speech-to-speech translation system, Alan Black, Ralf Brown, Robert Frederking, Rita Singh, John Moody and Eric Steinbrecher, Human Language Technology Conference (HLT 2002), San Diego, California, March 24-27, 2002.

  18. Automatic generation of sub-word units for speech recognition systems, Rita Singh, Bhiksha Raj and Richard M. Stern, IEEE Transactions on Speech and Audio Processing, vol. 10(2), pp. 89-99, Feb. 2002. ps

  19. Signal and feature compensation methods for robust speech recognition, Rita Singh, Richard M. Stern and Bhiksha Raj, In: Noise Reduction in Speech Applications (Electrical Engg, series), Ed. Gillian Davis, Chapter 9, pp. 221-246, CRC Press LLC, USA, 2002. About the book (pdf) and More details

  20. Model compensation and matched condition methods for robust speech recognition Rita Singh, Bhiksha Raj and Richard M. Stern, In: Noise Reduction in Speech Applications (Electrical Engg, series), Ed. Gillian Davis, Chapter 10, pp. 247-278, CRC Press LLC, USA, 2002

  21. Distributed speech recognition using codec parameters, Bhiksha Raj, Joshua Migdal and Rita Singh, Proc. Automatic Speech Recognition and Understanding workshop (ASRU 2001), Trento, Italy, Dec. 9-13, 2001.

  22. Speech in noisy environments: robust automatic segmentation, feature extraction, and hypothesis combination, Rita Singh, Michael L. Seltzer, Bhiksha Raj and Richard M. Stern, Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP 2001), Salt Lake City, Utah, May 7-11 2001 ps

  23. Tandem acoustic modeling in large-vocabulary recognition, Daniel P. W. Ellis, Rita Singh and Sunil Sivadas, Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP 2001), Salt Lake City, Utah, May 7-11 2001 pdf

  24. Structured redefinition of sound units for improved speech recognition, Rita Singh, Bhiksha Raj, and Richard M. Stern, Proc. 6th Intl. Conf. on Speech and Language Processing (ICSLP 2000), Beijing, China, Oct. 16-20 2000 ps

  25. Automatic subword unit refinement via phone splitting for spontaneous speech recognition, Jon P. Nedel, Rita Singh, and Richard M. Stern, Proc. 6th Intl. Conf. on Speech and Language Processing (ICSLP 2000), Beijing, China, Oct. 16-20 2000 pdf

  26. Phone transition acoustic modeling: application to speaker independent and spontaneous speech systems, Jon P. Nedel, Rita Singh, and Richard M. Stern, Proc. 6th Intl. Conf. on Speech and Language Processing (ICSLP 2000), Beijing, China, Oct. 16-20 2000 pdf

  27. Task and domain specific modelling in the Carnegie Mellon Communicator, Alexander I. Rudnicky, Christina Bennett, Alan W. Black, Ananlada Chotimongcol, Kevin Lenzo, Alice Oh, Rita Singh, Proc. 6th Intl. Conf. on Speech and Language Processing (ICSLP 2000), Beijing, China, Oct. 16-20 2000 pdf

  28. Automatic generation of phone-sets and lexical transcriptions, Rita Singh, Bhiksha Raj, and Richard M. Stern, Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP 2000), Istanbul, Turkey, June 5-9, 2000 ps

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

  30. Domain adduced state tying for cross domain acoustic modeling, Rita Singh, Bhiksha Raj, and Richard M. Stern, Proc. 6th European Conference on Speech Communication and Technology (EUROSPEECH 1999), Budapest, Hungary, Sept. 5-9 1999 ps

  31. Automatic clustering and generation of contextual questions for tied states in hidden Markov models, Rita Singh, Bhiksha Raj, and Richard M. Stern, Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP 1999), Phoenix, Arizona, May 15-19, 1999 ps

  32. Inference of missing spectrographic features for robust speech recognition, Bhiksha Raj, Rita Singh, and Richard M. Stern, Proc. 5th Intl. Conf. on Spoken Language Processing (ICSLP 1998), Sydney, Australia, Nov. 30 - Dec. 4, 1998 ps
These are my publications in speech since 1998. My earlier publications (1993-1998) were on chaos theory, signal design, and geodynamics.