Ciprian Chelba- Defended his doctoral thesis: "Exploiting Syntactic Structure for Natural Language Modeling" on December 17, 1999 and has taken a position with Microsoft Corporation.
Chelba, C. and Jelinek, F."Exploiting Syntactic Structure for Language Modeling" > Proceedings of COLING-ACL'98, Montreal, Canada, pp. 225-231, vol. 1., 1998.
Chelba, C. "A Structured Language Model" (pdf) in the Proceedings of the Annual Meeting of the Association for Computational Linguistics and Conference of the European Chapter of the Association for Computational Linguistics, in Madrid Spain, July 7-12, 1997.
Chelba, C., Jelinek, F., Khudanpur, S., et al. "Structure and Performance of a Dependency Language Model" (pdf) in the Proceedings of the Fifth European Conference on Speech Communication and Technology (EuroSpeech'97), in Rhodes Greece, September 22 - 25, 1997, p.p. 2775-2778.
Xiaoqiang Luo- Defended his doctoral thesis: "Balancing Model Resolution and Generalizability in Large Vocabulary Continuous Speech Recognition" on February 15, 1999 and has taken a position with IBM.
Luo, X. and Jelinek, F. "Probabilistic Classification of HMM States for Large Vocabulary Continuous Speech Recognition," Proceedings of the 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing, Phoenix, Arizona, March 15-19, 1999, Vol. I, p.p. 353-356.
Luo, X. and Jelinek, F. "Nonreciprocal Data Sharing in Estimating HMM Parameters", in the Proceedings of ICSLP-98, Sydney, Australia, 1998, p.p. 65-68.
Luo, X. "Growth Transform of A Sum of Rational Functions and Its Application in Estimating HMM Parameters", accepted for publication in the Proceedings of the International Conference on Speech Science and Technology (SST-98), Sydney, Australia, 1998.
Luo, X. and Jelinek, F. "Improving HMM State Tying," Proceedings of the Hub-5 Conversational Speech recognition (LVCSR) Workshop, Linthicum, Maryland, September 24-25, 1998.
Luo, X. and Roukos, S. "An Iterative Algorithm to Build Chinese Language Models," Proceedings of the 34th Annual ACL Conference, June 24-27, Santa Cruz, CA, pp. 139-143, 1996.
McDonough, J., Byrne, W., and Luo, X. "Speaker Normalization with All-Pass Transforms" in the Proceedings of the 5th International Conference on Spoken Language Processing, Sydney, Australia, November 30-December 4, 1998. Vol. 6, pp. 2307-2310.
Lidia Mangu- Left to take a full time position with IBM in January 2000. She returned and defended her doctoral dissertation: "Finding Consensus in Speech Recognition" April, 2000.
Mangu, L., Brill, E., and Stolcke, A. Improve Accuracy by Local Consensus (pdf) In Proc. Hub-5/Conversational Speech Understanding Workshop, Linthicum, MD.
John McDonough- Defended his doctoral dissertation: "Speaker Comprehension with All-Pass Transforms" on March 30, 2000. He has taken a position at the Universitaet Karlsruhe with Dr. Alex Waibel.
Byrne, W., Hajic, J., Ircing, P., Jelinek, F., Khudanpur, S., McDonough, J., Peterek, N., Psutka, J. "Large Vocabulary Speech Recognition for Read and Broadcast Czech," accepted to TSD'99, Marienbad, Czech Republic.
Byrne, W., Finke, M., Khudanpur, S., McDonough, J., Nock, H., Riley, M., Saraclar, M., Wooters, C. and Zavaliagkos, G. "Pronunciation Modelling Using a Hand-Labelled Corpus for Conversational Speech Recognition," IEEE International Conference on Acoustics, Speech and Signal Processing, Seattle, WA, 1998.
McDonough, J. and Byrne, W. "Speaker Adaptation with All-Pass Transforms," accepted to the 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing, Phoenix, Arizona, March 15-19, 1999, Vol. II, p.p. 757-760
McDonough, J. and Byrne, W. "Single-Pass Adapted Training with All-Pass Transforms," submitted to EuroSpeech-99, Budapest, Hungary.
McDonough, J., Byrne, W., and Luo, X. "Speaker Normalization with All-Pass Transforms" in the Proceedings of the 5th International Conference on Spoken Language Processing, Sydney, Australia, November 30-December 4, 1998. Vol. 6, pp. 2307-2310.
Riley, M., Byrne, W., Finke, M., Khudanpur, S., Ljolje, A., McDonough, J., Nock, H., Saraclar, M., Wooters, C., and Zavaliagkos, G. "Stochastic pronunciation modeling from hand-labelled phonetic corpora," to appear, Speech Communication.
Riley, M., Byrne, W., Finke, M., Khudanpur, S., Ljolje, A., McDonough, J., Nock, H., Saraclar, M., Wooters, C., and Zavaliagkos, G. "Stochastic pronunciation modeling from hand-labelled phonetic corpora," in the Proceedings of the workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, The Netherlands, May 4-6, 1998.
Saraclar, M., Byrne, W., Finke, M., Khudanpur, S., McDonough, J., Nock, H., Riley, M., Wooters, C., and Zavaliagkos, G. "Pronunciation Modeling Using a Hand-Labelled Corpus for Conversational Speech Recognition." ICASSP'98 Conference Proceedings, Vol. I, pp. 313-316, Seattle, WA, 1998.
Murat Saraclar- Defended his doctoral dissertation "Pronunciation Modeling for Conversational Speech Recognition" on May 23, 2000.
Byrne, W., Finke, M., Khudanpur, S., McDonough, J., Nock, H., Riley, M., Saraclar, M., Wooters, C. and Zavaliagkos, G. "Pronunciation Modelling Using a Hand-Labelled Corpus for Conversational Speech Recognition," IEEE International Conference on Acoustics, Speech and Signal Processing, Seattle, WA, 1998.
Byrne, W., Khudanpur, S., and Saraclar, M. "A Pronunciation Modeling Update from CLSP," in the Proceedings of the Hub-5 Conversational Speech Recognition Workshop, Linthicum Heights, MD, November 4-6, 1997.
Byrne, W., Khudanpur, S., Saraclar, M., et al. "Pronunciation Modeling for Conversational Speech Recognition - A Status Report from WS97," in the Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding, Santa Barbara, CA, pp. 26-33, 1997.
Fosler, E., Weintraub, M., Wegmann, S., Kao, Y-H., Khudanpur, S., Galles, C., and Saraclar, M. "Automatic Learning of Word Pronunciation from Data," in the Proceedings Addendum of the Int'l Conference on Spoken Language Processing, Philadelphia, PA, pp.28-29, October 1996.
Nock, H. and Saraclar, M. "Pronunciation Modeling Update from CLSP," Proceedings of the Hub-5 Conversational Speech recognition (LVCSR) Workshop, Linthicum, Maryland, September 24-25, 1998.
Riley, M., Byrne, W., Finke, M., Khudanpur, S., Ljolje, A., McDonough, J., Nock, H., Saraclar, M., Wooters, C., and Zavaliagkos, G. "Stochastic pronunciation modeling from hand-labelled phonetic corpora," to appear, Speech Communication.
Riley, M., Byrne, W., Finke, M., Khudanpur, S., Ljolje, A., McDonough, J., Nock, H., Saraclar, M., Wooters, C., and Zavaliagkos, G. "Stochastic pronunciation modeling from hand-labelled phonetic corpora," in the Proceedings of the workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, The Netherlands, May 4-6, 1998.
Saraclar, M., Nock, H., and Khudanpur, S. "Pronunciation Modeling by Sharing Gaussian Densities Across Phonetic Models," submitted to EuroSpeech'99, Budapest, Hungary.
Dimitra Vergyri- Defended her doctoral dissertation "Integration of Multiple Knowledge Sources in Speech Recognition Using Minimum Error Training" on May 15, 2000.
Rosenfeld, R., Agarwal, R., Byrne, W., Iyer, R., Liberman, M., Shriberg, L., Unverferth, J., Vergyri, D., and Vidal, E. "Error Analysis and Disfluency Modeling in the Switchboard Domain," Proceedings Addendum of ICLSP 96, Philadelphia, PA, p. 15, October 1996.
