Constantinos Boulis

University of Washington Work: 206-543-4868

Department of Electrical Engineering Email:

Paul Allen Center - Room AE100R

Campus Box 352500

Seattle, WA 98195-2500

Objective

To find a position in applied research and development on natural language processing, automatic speech recognition and data mining.

Skills

  • Κnowledge of statistical learning algorithms, both supervised and unsupervised. Text classification, text clustering, data mining, training and inference on Bayesian & Markov Networks. Sequence models, such as Hidden Markov Models. Core speech recognition algorithms.
  • 8 years of software development in C,C++, Perl, Matlab on Linux/Unix platform. Contributed on software projects of tens of thousand of lines of code, such as Stanford Research Institute (SRI) Decipher and Microsoft Research Whisper systems, both systems of large vocabulary speech recognition.

Education

PhD,Electrical Engineering,September 2005

University of Washington, Seattle, WA, USA

Dissertation: "Topic Learning in Text and Conversational Speech"

Advisor: Professor Mari Ostendorf

MPhil, Computer Engineering, August 2000

Technical University of Crete, Greece

Thesis: "Maximum Likelihood Stochastic Adaptation using Medium and Small Data Sets"

Advisor: Professor Vassileios Digalakis

Diploma (5 year study program with thesis), Computer Engineering, December 1998

Technical University of Crete, Greece

Thesis: "Rapid Speaker Adaptation using Markov Random Fields" (in Greek)

Advisor: Professor Vassileios Digalakis

Awards

  • Outstanding Graduate Research Assistant Award, Electrical Engineering Dept., Univ. of Washington, 2005
  • Best student paper award, PKDD 2004
  • Second place in Ericsson Award of Excellence for undergraduate theses related to communication, 2000

Experience

Research Assistant : September 2001 - present

Department of Electrical Engineering, University of Washington

Researching methodologies on extracting topic information from speech and text databases. Developing new algorithms for combining clustering partitions and feature selection for text. Also, investigating issues

pertinent to spoken language understanding such as the role of prominence, disfluencies, gender and word errors.

Research Intern : June 2001 - August 2001

Speech Technologies Group, Microsoft Research

Worked on a client-server approach to speech recognition for hand-held devices. Developed different source and channel coders that offered improvements compared to existing baselines.

Research Assistant : September 2000 - June 2001

Department of Electrical Engineering, University of Washington

Worked on the design of a client-server architecture for speech recognition using lightweight hand-held communication devices and a remote ASR server. Developed source and channel coding algorithms offering robustness to packet losses under manageable total delay. Experiments were conducted on the Defense Advanced Research Projects Agency (DARPA)Communicator database.

Research Assistant : January 1999 - August 2000

Department of Computer Engineering, Technical University of Crete, Greece

Work involved exploring a new speaker adaptation algorithm to work under small amounts of adaptation data. Experiments were conducted on the Wall Street Journal database. Also, implemented an adaptation tool to be used in a system of automatic large vocabulary dictation in Greek. The implementation included methods for combining different speaker adaptation algorithms.

Teaching Assistant : February 1999 - June 1999

Department of Computer Engineering, Technical University of Crete, Greece

Conducted classroom exercises and graded homework assignments for the undergraduate course "Analog Telecommunication Systems".

Visiting Scholar : June 1998 - August 1998

Center for Speech and Language Processing, Johns Hopkins University

Worked as part of a team with the goal to introduce algorithms for speaker adaptation under limited resources.

Journal Publications

Deng, L., Wang, Y., Wang, K., Acero, A., Hon, H.-W., Droppo, J., Boulis, C., Mahajan, M., and Huang, X.D, February-March 2004, “Speech and Language Processing for Multimodal Human-Computer Interaction”, Journal of VLSI Signal Processing Systems, 36(2-3):161-187.

Boulis, C., Ostendorf, M., Riskin, E., Otterson, S. November 2002. “Graceful Degradation of Speech Recognition Performance Over Packet-Erasure Networks”, IEEE Transactions on Speech and Audio Processing, 10(8):580-590.

Deng, L., Wang, K., Acero, A., Hon, H.-W., Droppo, J., Boulis, C., Wang, Y.-Y., Jakoby, D., Mahajan, M., Chelba C., and Huang, X.D. November 2002. “Distributed Speech Processing in MiPad's Multimodal User Interface”, IEEE Transactions on Speech and Audio Processing, 10(8):605-619.

Boulis, C., Diakoloukas, V., Digalakis, V. July 2001. “Maximum Likelihood Stochastic Transformations Adaptation for Medium and Small Data Sets”. Computer Speech and Language, 15(3):257-287.

Conference Publications

Boulis, C., Ostendorf, M., September 2005. “Using Symbolic Prominence to Help Design Feature Subsets for Topic Classification and Clustering of Natural Human-Human Conversations”, Interspeech-05, pp. 425-428.

Boulis, C., Kahn, J., Ostendorf, M., July 2005. “The Role of Disfluencies in Topic Classification of Natural Human-Human Conversations”, Proc. of the Workshop on Spoken Language Understanding, pp 9-14.

Boulis, C., Ostendorf, M., June 2005. “A Quantitative Analysis of Lexical Differences Between Genders in Telephone Conversations”, Proc. of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL), pp. 435-442.

Boulis, C., Ostendorf, M. April 2005. “Text Classification by Augmenting the Bag-of-Words Representation with Redundancy-Compensated Bigrams”, Proc. of the International Workshop on Feature Selection in Data Mining, pp 9-16.

Boulis, C., Ostendorf, M. September 2004. “Combining Multiple Clustering Systems”. Proc. of the 8th European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD), LNAI 3202, pp. 63-74.

Boulis, C. May 2004. “Speaker Recognition with Mixtures of Gaussians with Sparse Regression Matrices”, Proc. of the Student Research Workshop of Human Language Technology/North American Chapter of the Association for Computational Linguistics (HLT/NAACL), companion volume, pp. 55-60.

Riskin, E., Boulis, C., Otterson, S., Ostendorf, M. September 2001. “Graceful Degradation of Speech Recognition Performance Over Lossy Packet Networks”. Proc. of the 7th European Conference on Speech Communication and Technology (Eurospeech 2001), pp. 2715-2719.

Boulis, C., Digalakis, V. June 2000. “Fast Speaker Adaptation of Large Vocabulary Continuous Speech Recognizer Using a Basis Transform Approach”, Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 989-992.

Digalakis, V., Bocchieri, E., Boulis, C., Byrne, W., Collier, H., Corduneanu, A., Kannan, A., Khudanpur, S., Sankar, A. May 1999. “Rapid Speech Recognizer Adaptation to New Speakers”, Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 765-768.

Bocchieri, E., Digalakis, V., Corduneanu, A., Boulis, C., May 1999. “Correlation Modeling of MLLR Transform Biases for Rapid HMM Adaptation to New Speakers”, Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 773-776.

Major Citations

The following papers have been cited in peer-reviewed journals, conferences and workshops more than 5 times:

"Graceful Degradation of Speech Recognition Performance Over Packet-Erasure Networks" (22 citations).

"Rapid Speech Recognizer Adaptation to New Speakers" (20 citations).

Patents

Droppo, J., Acero, A., Boulis, C. Method of Reducing Index Sizes Used to Represent Spectral Content Vectors (granted May 27 2004, #20040102972)

References

Professor Mari Ostendorf

Department of Electrical Engineering, University of Washington, Seattle,

Dr. Jasha Droppo

Researcher, Microsoft Research, Speech Technologies group,

Professor Eve Riskin

Department of Electrical Engineering, University of Washington, Seattle,