my picture

Sameer R. Maskey, PhD                                              

Adj. Assistant Professor, Columbia University

Ph.D, 2008, Columbia University (Computer Science)
M.S, 2005, Columbia University (Computer Science)
B.S. 2002, Bates College, (Math and Physics)


Sameer Maskey teaches Statistical Methods/Machine Learning for Speech and Natural Language Processing at Columbia University. He has published more than 20 papers in International Conferences and Journals, and has filed several patents. He is also a Founder of technology startup based out of New York. He has served as a Session Chair, a Program Committee member, and a Review Committee member of many International Conferences including ACL, HLT, ICASSP, NAACL and COLING. He also worked as a Research Staff Member (Research Scientist) at IBM T.J Watson Research Center where he invented various statistical algorithms to improve Speech-to-Speech translation and Question Answering systems. He received his PhD in Computer Science from Columbia University and Bachelors (Honors) in Mathematics and Physics from Bates College. He has worked on wide range of topics that deal with large amount of data and Machine Learning methods.


Spring 2014
Data Science and Technology Entrepreneurship

Fall 2013
Lean LaunchPad - Part of teaching team with Steve Blank and Bob Dorf

Programming for Entrepreneurs

Spring 2013
Syllabus Data Science and Technology Entrepreneurship
(Taught across two Schools - Columbia Business School and Computer Science Department)
More information for MBA students/CS students

Fall 2012
Statistical NLP for the Web

Spring 2010
Statistical Methods for Natural Language Processing (COMS E6998-7)

Recent Professional Activities

Reviewer, ICASSP, 2013
Invited Attendee, NSF Workshop, UPenn, 2012
Reviewer, Association for Computational Linguistics : ACL 2012
Reviewer, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2012
Reviewer, Interspeech, 2012
Review Committee, Association for Computational Linguistics : NAACL-HLT 2012
Tutorial Presenter, Association for Computational Linguistics : HLT (ACL-HLT) 2011
Reviewer, ACM Transactions on Speech and Language Processing, 2011
Review Committee, Association for Computational Linguistics : HLT (ACL-HLT) 2011
Reviewer, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2011
Reviewer, Interspeech, 2011
Reviewer, Empirical Methods in Natural Language Processing (EMNLP), 2011
Session chair, COLING 2010
Review Committee, SLT 2010
Invited Talk, CUNY 2010
Invited Lecture, Columbia University, 2010
Reviewer, Interspeech 2010
Reviewer, ACL 2010
Reviewer, HLT 2010
Program Committee Member, ASRU 2009
Reviewer, Journal of Computer Speech and Language, 2009
Reviewer, International Conference on Audio, Speech and Signal Processing, 2009
Reviewer, Journal: Transaction of Audio, Speech and Language Processing, 2008 - present
Reviewer, Journal : IEEE letters, 2008
Reviewer, International Conference on Speech and Language Processing, 2008, 2009
Reviewer, Journal of Data Knowledge & Engineering, 2008



22) Maskey, S.R., Zhou. B, "Unsupervised Deep Belief Features for Speech Translation," Interspeech 2012, Portland, Oregon pdflink

21) Maskey, S.R., Rosenberg, A., "Power Mean Pyramid Scores for Summarization Evaluation," Interspeech 2012, Portland, Oregon pdflink


20) Zhou, B., Cui, X., Huang, S., Cmejrek, M., Zhang, W., Xue, J., Cui, J., Xiang, B., Daggett, G., Chaudharu, U., Maskey, S.R., Marcheret, E., The IBM Speech-to-Speech Translation System for Smartphone: Improvements for Resource-Constrained Tasks, Journal of Computer Speech and Language, 2011

19) Maskey, S.R., Rennie S.J, Zhou, B., "A Power Mean Based Algorithm for Combining Multiple Alignment Tables ", COLING 2010, Beijing China pdflink

18) Sainath, T, Maskey, S.R., Ramabhadran, B., Kanevsky, D., Nahamoo, D., Hirschberg, J., "Sparse Representations for Text Categorization ", Interspeech, 2010, Japan pdflink

17) Maskey, S.R., Rennie S.J, Zhou, B., "Combining Many Alignments for Speech to Speech Translation ", Interspeech, 2010, Japan pdflink

16) Maskey, S.R., Zhou, B., "Rapid Integration of Parts of Speech Information to Improve Reordering Model for English-Farsi Speech to Speech Translation ", ICASSP, March 2010, Dallas, US pdflink


15) Maskey, S.R., Dakka, W., "Named Entity Network Using Wikipedia", Interspeech 2009, Brighton, UK pdflink

14) Sarikaya, R., Maskey, S.R. , Zhang, R., Jan, E., Wang, D., Ramabhadran, B., Roukos, S., "Iterative Sentence-Pair Extraction from Quasi-Parallel Corpora for Machine Translation", Interspeech 2009, Brighton, UK pdflink

13) Maskey, S.R., Sethy, A., "Resampling Auxiliary Data for Language Model Adaptation in Machine Translation for Speech ", ICASSP 2009, Taiwan pdflink


12) Maskey, S.R
, Cmejrek, M., Zhou, B., Gao, Y., "Class based Named Entity Translation for Speech to Speech Translation System,", Spoken Language Technology, 2008, Goa, India pdflink

11) Maskey, S.R., Rosenberg, A., Hirschberg, J., "Intonational Phrases for Speech Summarization," Interspeech 2008, Brisbane, Australia pdflink

10) Mari Ostendorf, Benoit Favre, Ralph Grishman, Dilek Hakkani-Tur, Mary Harper, Dustin Hillard, Julia Hirschberg, Heng Ji, Jeremy G. Kahn, Yang Liu, Maskey S.R., Evegeny Matusov, Hermann Ney, Andrew Rosenberg, Elizabeth Shriberg, Weng Wang and Chuck Wooters. "Speech Segmentation and its Impact on Spoken Document Processing", IEEE Signal Processing Magazine, Special Issue on Spoken Language Technology, May 2008 pdflink

Maskey, S.R., "Automatic Broadcast News Speech Summarization", PhD Thesis, Columbia University, New York, NY pdflink


9) Maskey, S.R., Zhou, B., Gao, Y., "A Phrase-Level Machine Translation Approach for Disfluency Detection Using Weighted Finite State Transducers", Interspeech 2006, Pittsburgh, PA pdflink

8) Maskey, S.R. & Hirschberg, J. "Soundbite Detection in Broadcast News Domain", Interspeech 2006, Pittsburgh, PA pdflink

7) Maskey, S.R. & Hirschberg, J. "Summarizing Speech Without Text Using Hidden Markov Models", HLT-NAACL 2006 (short), New York, NY pdflink


6) Maskey, S.R. & Hirschberg, J. "Comparing Lexial, Acoustic/Prosodic, Discourse and Structural Features for Speech Summarization", Eurospeech 2005, Lisbon, Portugal pdflink

5) McKeown, K., Hirschberg, J., Galley, M., Maskey, S.R., “From Text to Speech Summarization”, ICASSP 2005, Philadelphia, PA pdflink


4) Maskey, S.R., Black, A.B., Tomokiyo, L.M., "Bootstrapping Phonetic Lexicon for New Languages", ICSLP 2004, South Korea. (best student paper nomination)pdflink

3) Maskey, S.R., Bacchiani, M., Roark, Brian., Sproat, R., "Improved Name Recognition using Meta-Data dependent Name Networks", ICASSP 2004, Montreal, Canada. pdflink

2) Thorisson, K., Benko, H., Abramov, D., Arnold, A., Maskey, S.R., Vaseekaran, A., "Constructionist Design Methodology for Interactive Intelligences", p 77-90, AI Magazine, Vol. 25, No. 4, Winter 2004.pdflink


1) Maskey, S.R. & Hirschberg, J., "Automatic Summarization of Broadcast News using Structural Features", Eurospeech 2003, Geneva, Switzerland.pdflink

Pending/Granted Patents

1. Maskey, S.R., Kanvesky, D., Sainath, T., Ramabhadran, B, "Individual S2S Health Package for Travelers Customized by Biometric" (IBM Patent disclosure YOR820100129)

2. Sainath, T., Caskey, S., Maskey, S.R., Kanvesky, D., "Using Biometric to Select Music Preferences" (IBM Patent disclosure YOR820120485)

3. Sainath T., Maskey S.R., Kanevsky, D., Ramabhadran, B, "Sparse Representation for Text Categorization" (IBM Patent Disclosure YOR820100420)

4. Caskey, S., Maskey, S.R., "Client Side Translation Cache Prediction to Improve Speed and Accuracy of Machine Translation Services" (IBM Patent Disclosure YOR820101118)

5. Sainath, T., Caskey, S., Maskey, S.R., Kanvesky, D., "Smart Copy Clipboard" (IBM Patent disclosure YOR820120217)

6. Sainath, T., Caskey, S., Maskey, S.R., Kanvesky, D., "Controlled Resources Based on Good Behaviour" (IBM Patent Disclosure YOR820110231)

7. Kanvesky, D., Maskey, S.R., Sainath, T., Ramabhadran, B, "Traveler Communicator" (IBM Patent disclosure YOR820100337)

8. Maskey, S.R., Zhou, B., Gao, Y., "Disfluency Detection for a Speech-to-Speech Translation System Using Phrase-level Machine Translation with Weighted Finite State Transducers" (Filed by IBM in August 2006)

9. Bacchiani, M., Maskey, S.R., Roark, B., Sproat, R., "A System and Method Using Meta-Data fo Spoken Dialog Systems" U. S. Prov. Application No: 60/515,896. Filed for International Patent as well. (Filed by AT&T in October 2003)