Damianos Karakos

Contact Information

Human Language Technology Center of Excellence
Stieff Building
Johns Hopkins University
Baltimore, MD 21218
Tel: 410-516-4792


I am a research scientist with the Human Language Technology Center of Excellence, and an assistant research professor with the Department of Electrical and Computer Engineering, Johns Hopkins University. I am also a member of the Center for Language and Speech Processing.

My research focuses on statistical and information-theoretic aspects of speech recognition and natural language processing, with an emphasis on language modeling, document categorization, and techniques for cross-instance tuning of statistical models.


Publications

PhD Dissertation

Journal Publications

[1] P.E. Trahanias, D. Karakos and A.N. Venetsanopoulos, Directional Processing of Color Images: Theory and Experimental Results, IEEE Trans. on Image Processing, Special Issue on Nonlinear Image Processing, Vol. 5, No. 6, pp. 868-880, June 1996.
[2] D. Karakos and P.E. Trahanias, Generalized Multichannel Image-Filtering Structures, IEEE Trans. on Image Processing, Special Issue on Color Imaging, Vol. 6, No. 7, pp. 1038-1045, July 1997.
[3] D. Karakos and A. Papamarcou, A Relationship Between Quantization and Watermarking Rates in the Presence of Additive Gaussian Attacks, IEEE Trans. on Information Theory, Vol. 49, No. 8, pp. 1970-1982, August 2003.
[4] B. Jedynak and D. Karakos, Finding a needle in a haystack: Conditions for reliable detection in the presence of clutter, Statistics and Probability Letters, Vol. 78, No. 5, pp. 471-480, April 2008.
[5] D. Karakos, S. Khudanpur, D. J. Marchette, A. Papamarcou and C.E.Priebe,On the Minimization of Concave Information Functionals for Unsupervised Classification via Decision Trees, Statistics and Probability Letters, Vol. 78, No. 8, pp. 975-984, June 2008.

Conference Publications

[1] N. Hardavellas, D. Karakos and M. Mavronicolas, Notes on Sorting and Counting Networks, in Proceedings of the 7th International Workshop on Distributed Algorithms (WDAG-93), A. Schiper, ed., pp. 234-248, Lecture Notes in Computer Science, Vol. 725, Springer-Verlag, Lausanne, Switzerland, September 1993.
[2] P.E. Trahanias, D. Karakos and A.N. Venetsanopoulos, Directional Segmentation of Color Images, in Proceedings of the 1995 IEEE Workshop on Nonlinear Signal and Image Processing, pp. 515-518, Neos Marmaras, Halkidiki, Greece, June 1995.
[3] D. Karakos and P.E. Trahanias, Combining Vector Median and Vector Directional Filters: The Directional-Distance Filters, in Proceedings of the 1995 IEEE International Conference on Image Processing (ICIP-95),pp. 171-174, Washington, DC, USA, October 1995.
[4] D. Karakos and A. Papamarcou, Relationship between Quantization and Distribution Rates of Digitally Watermarked Data, in Proceedings of the 2000 IEEE International Symposium on Information Theory (ISIT-2000),page 47, Sorrento, Italy, June 2000.
[5] D. Karakos and A. Papamarcou, Fingerprinting, Watermarking and Quantization of Gaussian Data, in Proceedings of the 2001 Allerton Conference on Communication, Control and Computing (Invited Talk),Monticello, Illinois, October 2001.
[6] D. Karakos and A. Papamarcou, A Relationship between Quantization and Watermarking Rates in the Presence of Gaussian Attacks, inProceedings of the 2002 Conference on Information Sciences and Systems (CISS-2002), Princeton, New Jersey, March 2002.
[7] C. E. Priebe, D. J. Marchette, Y. Park, E. Wegman, J. Solka, D. Socolinsky, D. Karakos, K. Church, R. Guglielmi, R. Coifman, D. Lin, D. Healy, M. Jacobs, A. Tsao, Iterative Denoising for Cross-corpus Discovery, inProceedings of the 2004 Symposium on Computational Statistics (Invited Talk), Prague, August 23-27, 2004.
[8] Daqing He, Dina Demner-Fushman, Douglas W. Oard, Damianos Karakos and Sanjeev Khudanpur, Improving Passage Retrieval Using Interactive Elicition and Statistical Modeling, in Proceedings of Text REtrieval Conference (TREC), 2004.
[9] D. Karakos, S. Khudanpur, J. Eisner and C. E. Priebe, Unsupervised Classification via Decision Trees: An Information-Theoretic Perspective, in Proceedings of the 2005 IEEE International Conference on Acoustics, Speech and Signal Processing (Invited Talk), Philadelphia, PA, March 18-23, 2005.
[10] J. Eisner and D. Karakos, Bootstrapping Without the Boot, inProceedings of the 2005 Conference on Human Language Technology / Empirical Methods in Natural Language Processing (HLT/EMNLP 2005), Vancouver, Canada, October 6-8, 2005.
[11] B. Pytlik, A. Ghoshal, D. Karakos and S. Khudanpur, TRECVID 2005 Experiments at Johns Hopkins University: Using Hidden Markov Models for Video Retrieval, in Proceedings of the 2005 TREC Video Retrieval Conference (TRECVID-2005), 2005.
[12] D. J. Marchette, C. E. Priebe, Y. Park, D. Karakos, Iterative Denoising for Adaptive Sensors, in Proceedings of the 2006 Hawaii International Conference on Statistics, Mathematics and Related Fields, Honolulu, Hawaii, January 16-18, 2006.
[13] D. Karakos and S. Khudanpur, Estimating Conditional Densities from Sparse Data for Statistical Language Modeling, in Proceedings of the 2006 Workshop on Information Theory and its Applications (Invited Talk), UCSD Campus, La Jolla, CA, February 6-10, 2006.
[14] J. Lin, D. Karakos, D. Demner-Fushman and S. Khudanpur, Generative Content Models for Structural Analysis of Medical Abstracts, inProceedings of the 2006 Workshop on Biomedical Natural Language Processing (BioNLP’06), New York City, New York, June 8, 2006.
[15] D. Karakos and S. Khudanpur, Language Modeling with the Maximum Likelihood Set: Complexity Issues and the Back-off Formula, inProceedings of the 2006 International Symposium on Information Theory (ISIT-06), Seattle, Washington, July 9-14, 2006.
[16] D. Karakos, S. Khudanpur, J. Eisner and C. E. Priebe, Iterative Denoising using Jensen-Renyi Divergences with an Application to Unsupervised Document Categorization, in Proceedings of the 2007 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP-07), Honolulu, Hawaii, April 15-20, 2007.
[17] D. Karakos, J. Eisner, S. Khudanpur and C. E. Priebe, Cross-Instance Tuning of Unsupervised Document Clustering Algorithms, inProceedings of the 2007 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT 2007), Rochester, NY, April 22-27, 2007.
[18] B. Jedynak and D. Karakos, Unigram Language Models using Diffusion Smoothing over Graphs, in Proceedings of the 2007 Workshop on Graph-based Methods for Natural Language Processing (TextGraphs-2), Rochester, NY, April 26, 2007.
[19] D. Karakos and S. Khudanpur, Error Bounds and Improved Probability Estimation using the Maximum Likelihood Set, in Proceedings of the 2007 IEEE International Symposium on Information Theory (ISIT-07), Nice, France, June 24-29, 2007.
[20] D. Karakos, J. Eisner, S. Khudanpur and M. Dreyer, Machine Translation System Combination using ITG-based Alignments, in Proceedings of the 2008 Conference of the Association for Computational Linguistics (ACL-08), Columbus, Ohio, June 15-20, 2008.
[21] D. Karakos, S. Khudanpur and C.E.Priebe, Computation of Csiszar’s Mutual Information of Order alpha, in Proceedings of the 2008 IEEE International Symposium on Information Theory (ISIT-08), Toronto, Canada, July 6-11, 2008.
[22] D. Karakos and S. Khudanpur, Sequential System Combination for Machine Translation of Speech, in Proceedings of the 2008 IEEE Workshop on Spoken Language Technology (SLT-08), Goa, India, December 15-18, 2008.
[23] H. Zhou, D. Karakos, S. Khudanpur, A. G. Andreou and C. E. Priebe, On Projections of Gaussian Distributions using Maximum Likelihood Criteria, in Proceedings of the 2009 Workshop on Information Theory and its Applications (Invited Talk), UCSD Campus, La Jolla, CA, February 8-13, 2009.
[24] A.-V.I. Rosti, E. Matusov, J. Smith, N.F. Ayan, and 10 more. Confusion network decoding for MT system combination In Joseph Olive, Caitlin Christianson, and John McCary, editors, Handbook of Natural Language Processing and Machine Translation: DARPA Global Autonomous Language Exploitation, pp. 333-361. Springer, 2011.
[25] H. Zhou, D. Karakos and A. G. Andreou, A Semi-supervised Version of Heteroscedastic Linear Discriminant Analysis, in Proceedings of the 2009 Conference of the International Speech Communication Association (Interspeech-2009), Brighton, UK, September 6-10, 2009.
[26] P. Xu, D. Karakos and S. Khudanpur, Self-Supervised Discriminative Training of Statistical Language Models, in Proceedings of the 2009 Automatic Speech Recognition and Understanding Workshop (ASRU-2009), Merano, Italy, December 13-17, 2009.
[27] D. Karakos, H. Zhou, P. Xu, S. Khudanpur, and A. G. Andreou, Two Self-supervised Learning Techniques for Speech Recognition, in Proceedings of the 2010 Workshop on Information Theory and its Applications (Invited Talk), UCSD Campus, La Jolla, CA, January 31-February 5, 2010.
[28] D. Karakos, J. Smith and S. Khudanpur, Hypothesis Ranking and Two-pass Approaches for Machine Translation System Combination, inProceedings of the 2010 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP-2010), Dallas, Texas, March 14-19, 2010.
[29] G. Zweig, P. Nguyen, D. Van Compernolle, K. Demuynck, L. Atlas, P. Clark, G. Sell, M. Wang, F. Sha, H. Hermansky, D. Karakos, A. Jansen, S. Thomas, S. G.S.V.S., S. Bowman, J. Kao, Speech Recognition with Segmental Conditional Random Fields: A Summary of the JHU CLSP 2010 Summer Workshop, in Proceedings of the 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP-2011), Prague, Czech Republic, May 22-27, 2011.
[30] S. Huang, D. Karakos and D. Xu, Radial Gaussianization with Cluster-Specific Bias Compensation, in Proceedings of the 2011 Workshop on Statistical Signal Processing (SSP-2011), Nice, France, June 28-30, 2011.
[31] D. Xu, Y. Cao and D. Karakos, Description of the JHU System Combination Scheme for WMT 2011, in Proceedings of the 2011 Workshop on Statistical Machine Translation (WMT-2011), Edinburgh, UK, July 30-31, 2011.
[32] D. Karakos, M. Dredze, K. Church, A. Jansen and S. Khudanpur,Estimating Document Frequencies in a Speech Corpus, in Proceedings of the 2011 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU-2011), Hawaii, December 11-15, 2011.
[33] S. Huang, D. Karakos, G. A. Coppersmith, K. W. Church and S. M. Siniscalchi, Bootstrapping a Spoken Language Identification System Using Unsupervised Integrated Sensing and Processing Decision Trees, in Proceedings of the 2011 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU-2011), Hawaii, December 11-15, 2011.
[34] A. Celebi, H. Sak, E. Dikici, M. Saraclar, M. Lehr, E. T. Prud’hommeaux, P. Xu, N. Glenn, D. Karakos, S. Khudanpur, B. Roark, K. Sagae, I. Shafran, D. Bikel, C. Callison-Burch, Y. Cao, K. Hall, E. Hasler, P. Koehn, A. Lopez, M. Post, D. Riley, Semi-Supervised Discriminative Language Modeling for Turkish ASR, to appear in Proceedings of the 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP-2012)Kyoto, Japan, 2012.
[35] P. Xu, S. Khudanpur, M. Lehr, E. T. Prud’hommeaux, N. Glenn, D. Karakos, B. Roark, K. Sagae, M. Saraclar, I. Shafran, D. Bikel, C. Callison-Burch, Y. Cao, K. Hall, E. Hasler, P. Koehn, A. Lopez, M. Post, D. Riley,Continuous Space Discriminative Language Modeling, to appear inProceedings of the 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP-2012), Kyoto, Japan, 2012.
[36] K. Sagae, M. Lehr, E. T. Prud’hommeaux, P. Xu, N. Glenn, D. Karakos, S. Khudanpur, B. Roark, M. Saraclar, I. Shafran, D. Bikel, C. Callison-Burch, Y. Cao, K. Hall, E. Hasler, P. Koehn, A. Lopez, M. Post, D. Riley,Hallucinated N-Best Lists for Discriminative Language Modeling, to appear in Proceedings of the 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP-2012), Kyoto, Japan, 2012.
[37] A.-V. I. Rosti, X. He, D. Karakos, G. Leusch, Y. Cao, M. Freitag, S. Matsoukas, H. Ney, J. R. Smith, B. Zhang, Review of Hypothesis Alignment Algorithms for MT System Combination via Confusion Network Decoding, to appear in Proceedings of the 2012 Workshop on Machine Translation (WMT-2012), Montreal, Canada, 2012.

Technical Reports

[1] D. Karakos and A. Papamarcou, Relationship between Quantization and Distribution Rates of Digitally Fingerprinted Data, Institute for Systems Research Technical Report, TR 2000-51, UMD, December 2000.
[2] D. Karakos and A. Papamarcou, A Relationship between Quantization and Watermarking Rates in the Presence of Gaussian Attacks, Institute for Systems Research Technical Report, TR 2001-50, UMD, December 2001.


Last Modification:

Johns Hopkins University

Johns Hopkins University, Whiting School of Engineering

Center for Language and Speech Processing
Hackerman 226
3400 North Charles Street, Baltimore, MD 21218-2608

Center for Language and Speech Processing