Shankar Kumar's home page

Hi! I am now a post-doctoral fellow at the Johns Hopkins University.

I was a Ph.D student at the Johns Hopkins University . I defended on September 27, 2004.

My dissertation was on Minimum Bayes-Risk Techniques in Automatic Speech Recognition and Statistical Machine Translation.

Thesis: pdf

Slides from my Thesis Defense: pdf

Slides from Department Seminar (Thesis Proposal): pdf

Current resume: pdf

My research interests are in Statistical Machine Translation and in Large Vocabulary Continuous Speech Recognition. In both these areas my work aims to develop novel estimation and decoding approaches and build automatic systems using statistical techniques.

I am a member of the Center for Language and Speech Processing in the Department of Electrical and Computer Engineering . My advisor is Prof. Bill Byrne .

In the summer of 2003, I took part in an interesting workshop on Syntax for Statistical Machine Translation . Our goal was to incorporate syntactic structure into a statistical MT system using various techniques.

I have been involved in building systems in the NIST Machine Translation evaluations (2002,2003,2004) and the NIST Large Vocabulary Speech Recognition evaluations (2001 and 2002) CLSP LVCSR Evaluation system

Publications

Journals and Research Notes

S. Kumar, Y. Deng and W. Byrne A Weighted Finite State Transducer Translation Template Model for Statistical Machine Translation Journal of Natural Language Engineering. To appear.

S. Kumar and W. Byrne A Weighted Finite State Transducer Translation Template Model for Statistical Machine Translation Research Note No. 48. Center for Language and Speech Processing.

V. Goel, S. Kumar and W. Byrne Segmental minimum Bayes-risk decoding for automatic speech recognition IEEE Transactions on Speech and Audio Processing, Vol 12(3), 234-250. 2004.

R. Sproat, A. Black, S. Chen, S. Kumar, M. Ostendorf and C. Richards Normalization of Non-Standard Words Computer Speech and Language, Vol 15(3), 287-333. 2001.

Conferences

S. Kumar and W. Byrne, Minimum Bayes-Risk Decoding for Statistical Machine Translation Proceedings of HLT-NAACL 2004, May 2004, Boston, MA, USA. Talk

F. J. Och, D. Gildea, S. Khudanpur, A. Sarkar, K. Yamada, A. Fraser, S. Kumar, L. Shen, D. Smith, K. Eng, V. Jain, Z. Jin, D. Radev, A Smorgasbord of Features for Statistical Machine Translation , Proceedings of HLT-NAACL 2004, May 2004, Boston, MA, USA.

W. Byrne, S. Khudanpur, W. Kim, S. Kumar, P. Pecina, P. Virga, P. Xu and D. Yarowsky The Johns Hopkins University 2003 Chinese-English Machine Translation System Proceedings of MT-Summit IX, September 2003, New Orleans, LA, USA. Talk

S. Kumar and W. Byrne A Weighted Finite State Transducer Implementation of the Alignment Template Model for Statistical Machine Translation Proceedings of HLT-NAACL 2003, May 2003, Edmonton, Canada. Talk

S. Kumar and W. Byrne Minimum Bayes-Risk Word Alignment of Bilingual Texts Proceedings of EMNLP 2002, July 2002, Philadelphia, PA, USA. Talk

S. Kumar and W. Byrne Risk Based Lattice Cutting for Segmental Minimum Bayes-Risk Decoding Proceedings of ICSLP 2002, September 2002, Denver, CO, USA. Poster

V. Goel, S. Kumar and W. Byrne Confidence Based Lattice Segmentation and Minimum Bayes-Risk Decoding Proceedings of Eurospeech 2001, September 2001, Aalborg, Denmark. Poster

V. Goel, S. Kumar and W. Byrne Segmental Minimum Bayes-Risk ASR Voting Strategies Proceedings of ICSLP 2000, October 2000, Beijing, China.

Workshops

S. Kumar, Y. Deng, and W. Byrne The Johns Hopkins University 2004 Chinese-English and Arabic-English Machine Translation Evaluation Systems NIST Machine Translation Workshop, Alexandria, VA, USA, June 2004.

W. Byrne, S. Khudanpur, W. Kim, S. Kumar, P. Pecina, P. Virga, P. Xu and D. Yarowsky The Johns Hopkins University 2003 Chinese-English Machine Translation System NIST Machine Translation Workshop, Gaithersburg, MD, USA, July 2003.

W. Byrne, V. Doumpiotis, S. Kumar, S. Tsakalidis and V. Venkataramani, The JHU 2002 RT-02 Large Vocabulary Speech Recognition System May 2002, Vienna, VA, USA

W. Byrne, A. Gunawardana, S. Kumar and V. Venkataramani, The JHU Hub-5 Conversational Speech Transcription System, May 2001, Linthicum Heights, MD, USA.

Shankar Kumar
Last modified: Sat May 8 18:04:16 EDT 2004