4146 Murray Avenue Pittsburgh PA 15217-2704

Phone +1 412 521 3023 E-mail witbrock@cs.cmu.edu

	Michael Witbrock
Professional Interests	Unsupervised learning techniques for natural language processing including induction of syntactic and semantic structure of language from text corpora and from interaction with language users. Using the results of information retrieval as input to more sophisticated natural language processing including question answering and computerised natural-language translation. Applying learning algorithms to speech recognition, speech synthesis, and speech understanding systems, and more generally, learning and information processing algorithms motivated from neuroanatomy and physiological psychology. Parallel computer architecture and parallel algorithm design, including distributed applications and distributed linguistic data acquisition and other forms of machine learning using the internet.
Education	1986 - 1995 Carnegie Mellon University Pittsburgh, PA, USA   Ph.D. in Computer Science   Thesis Title: Learning Models of Speaker Variation   1980 - 1984 University of Otago Dunedin, New Zealand   B.Sc. (Hons) in Psychology   Specialised in Cognitive and Physiological Psychology. Degree awarded with First Class Honours. Substantial minor in Computer Science
Languages	Spoken: English, French. Read: Spanish
Citizenship	New Zealand Citizen, currently working for Carnegie Mellon on H1B Visa
Employment History	1996 - 1997 Carnegie Mellon University Pittsburgh, PA, USA   System Scientist  Work on speech recognition, information retrieval and natural language processing for the Informedia Project. 1995 - 1996 Carnegie Mellon University Pittsburgh, PA, USA   Post Doctoral Fellow  Development work on the Informedia Digital Video Library. Designed substantial sections of the user interface. Worked on improving the use of speech recognition for indexing. Created automatic digital fast forward using semantics to weight material. Worked on improving the natural language system used to query the library. Project Leader: Dr. Howard Wactlar.  Summer 1991 IBM T.J. Watson Research Hawthorne, NY, USA  Summer Intern  Evaluated the suitability of the GF11 SIMD architecture for molecular dynamics simulations. Designed and implemented a fast general message passing communication system for GF11 using its Benes network. Manager: Dr. Manoj Kumar.  Summer - 1991 CNET Lannion, France  Stage (Summer Intern)   Research on using connectionist learning techniques to characterise speaker voice variability. Conducted at the Centre National d’Études des Télécommunications. Manager: Dr. Christel Sorin. Summer 1990 IBM T.J. Watson Research Yorktown, NY, USA   Summer Intern  Designed and implemented parallel LU decomposition and matrix inversion routines for GF11. Extended programming tools to handle communications requirements for this task. Used RS6000s to work on neural network recognition of structure in sequential inputs. Manager: Dr. Manoj Kumar. Summer 1989 IBM T.J. Watson Research Yorktown, NY, USA  Summer Intern  Designed and implemented a backpropagation neural network simulator for GF11. The resulting program was the fastest existing backpropagation simulator. Manager: Dr. David A George. Summer 1991 IBM T.J. Watson Research Hawthorne, NY, USA  Summer Intern   Evaluated the suitability of the GF11 SIMD architecture for molecular dynamics simulations. Designed and implemented a fast general message passing communication system for GF11 using its Benes network. Manager: Dr. Manoj Kumar.     1984 1986 Text Understanding Systems Dunedin, New Zealand  Senior Programmer/Analyst  Senior Programmer/Analyst on a project to produce an automatic natural-language translation System for microcomputers based on SYSTRAN. Was responsible for directing a team of eight programmers, and for working with the company's linguists on system design. Director: Dr. Peter Toma 1983 1984 University of Otago Dunedin, New Zealand  Research Assistant  Research Assistant. Worked on development of an automated system for staging sleep EEGs. Also responsible for recording and manual analysis of EEGs. Supervisor: Dr. David. F. Marks.  1982 1983 University of Otago Dunedin, New Zealand  Research Assistant  Designed and implemented a raster graphics library for Otago University's computer graphics project. Also worked on hardware for graphical input devices and computer interconnect. Supervisor: Dr. Geoffrey Wyvill. 1978 1979 Wellcome Medical Research Dunedin, New Zealand   Research Programmer   Implementation of automated system for analysing grip strengths for hands of arthritic patients. Supervisor: Dr. Myers.
Teaching Experience	Spring 1997: Carnegie Mellon University, Computer Science.  Assisting with Introductory AI course. Lecturing on Logic-Based Agents, Speech Recognition, and designing assignments on Logic and on Neural Networks.  Autumn 1988: Carnegie Mellon University, Computer Science.  Teaching Assistant for Introductory AI course. Prepared and presented two lectures, designed and graded homework assignments and exam questions.  1994: Otago University, Psychology.  Laboratory tutor for Introduction to Experimental Methods. Taught and graded one half of a full year laboratory course.
Publications	Witbrock, M.J and Hauptmann, A.G. "Speech Recognition in a Digital Video Library", to appear in JASIS: Journal of the American Society for Information Science, 1997  Witbrock, M.J, and Hauptmann, A.G., "Using Words and Phonetic Strings for Efficient Information Retrieval from Imperfectly Transcribed Spoken Documents", to appear in DL97, The Second ACM International Conference on Digital Libraries, July 23 - 26, 1997, Philadelphia.  Hauptmann, A.G., Witbrock, M.J. and Christel, M.A. "Artificial Intelligence Techniques in the Interface to a Digital Video Library", CHI 97  Hauptmann, A.G. and Witbrock, M.J., "Informedia: News-on-Demand - Multimedia Information Acquisition and Retrieval", to appear in Maybury, M. (ed). Intelligent Multimedia Information Retrieval AAAI Press/MIT Press 1996. (in press)  Hauptmann, A.G., Witbrock, M.J. Rudnicky, A.I., and Reed, S., "Speech for Multimedia Information Retrieval", UIST-95: Proceedings of User Interface Software and Technology, Pittsburgh, PA, November, 1995.  Hauptmann, A.G., Witbrock, M.J., and Christel, M.G. "News-on-Demand: An Application of Informedia Technology", D-LIB Magazine, September, 1995.  Fischer, Michael., Meyer, Michael., and Witbrock, Michael. "User Extensibility in Amiga Mosaic", Proceedings of the Second International World Wide Web (WWW) Conference '94: Mosaic and the Web, October 1994.  Witbrock, Michael and Haffner, Patrick. "Rapid Connectionist Speaker Adaptation", Proceedings of the IEEE 1992 International Conference on Acoustics, Speech, and Signal Processing, March, 1992.  Witbrock, Michael and Zagha, Marco. "Back-Propagation Learning on the IBM GF11", Chapter in Przytula, K.W., and Prasanna Kumar, V.K. Parallel Digital Implementations of Neural Networks. PTR Prentice-Hall. Englewood Cliffs. 1993.  Witbrock, Michael and Zagha, Marco. "An Implementation of Back-Propagation Learning on GF11, a Large SIMD Parallel Computer", Parallel Computing 14 (1990) pp 329-346, North-Holland, Amsterdam  Franzini, M.A., Witbrock. M.J. and Lee, K.F. "Speaker-Independent Recognition of Connected Utterances Using Recurrent and Non-recurrent Neural Networks", Proceedings of the I.E.E.E. International Joint Conference on Neural Networks, June, 1989.  Franzini, M.A., Witbrock, M.J. and Lee, K. "Connectionist Approaches to Continuous Speech Recognition". Proceedings of the IEEE 1989 International Conference on Acoustics, Speech, and Signal Processing, May, 1989.  Lang, K.J. and Witbrock, M.J. "Learning to Tell Two Spirals Apart" in Touretzky, D.S., Hinton, G.E., and Sejnowski, T. (Eds) Proceedings of 1988 Connectionist Models Summer School
Professional memberships	Association for Computational Linguistics, Association for Computing Machinery, Sigma Xi
Invited Talks and Professional Duties	"Integrating Speech, Natural Language, Image Processing and Information Retrieval: The Informedia Digital Video Library Project", April 4th 1997, Machines that Learn Conference, Snowbird, Utah.  Co-chair of AAAI Spring Symposium on "Intelligent Integration of Text, Image, Video and Audio Corpora", March 1997, Stanford.