Email: vgoel@jhu.edu, vgoel@bme.jhu.edu
Cell Phone: (410) 905-1877
Lab Phone: (410) 516-5458,5409
Lab Fax: (410) 516-5050
Home phone: (410) 420-1352

    Automatic Speech Recognition; Statistical Modeling and Learning;
    Classification and Decision Theory; Information Theory and Statistics;

Ph.D., July 2000 (expected), Biomedical Engineering, Johns Hopkins University
    Dissertation: Minimum Bayes-risk automatic speech recognition.
    Advisors: Dr. William J. Byrne and Dr. Frederick Jelinek.
    GPA: 4.0/4.0

M.S.E., May 1995, Biomedical Engineering, Johns Hopkins University
    Thesis: A novel technique for EEG signal processing.
    Advisor: Dr. Nitish V. Thakor.
    GPA: 3.95/4.0

B.Tech., May 1993, Electrical Engineering, Indian Institute of Technology, Kanpur, India
    Thesis: Automated strain analysis using techniques of image processing.
    Advisor: Dr. S. K. Mullick.
    GPA: 10.0/10.0

The Bell Laboratories, Lucent Technologies, Murray Hill, NJ

Summer Intern, May 1997 - Jul 1997
    Project: Maximum likelihood lexical modeling.
    Supervisor: Dr. Frank K. Soong

Summer Intern, Jun 1996 - Aug 1996
    Project: Single pass real time A-star decoder implementation.
    Supervisor: Dr. Frank K. Soong

Indian Telephone Industries, Naini, India

Summer Engineer, May 1992 - Jul 1992
    Project: Optimization of production and inventory control of MARR systems.

Center for Language and Speech Processing, Johns Hopkins University

Research Assistant, Jan 1996 - Present
    Design of task specific speech recognizers under the minimum Bayes-risk (MBR)
    classification framework. Formulated a novel prefix-tree based multi-stack A-star
    algorithm to implement the MBR decoders. Shown that these decoders yield significant
    error rate reduction on tasks such as minimum word error rate transcription, keyword
    spotting, named entity detection, and gene identification from genomic DNA. Developed
    the idea of segmental MBR decoding in which a complex MBR decoder is approximated
    by a sequence of simple MBR decoders. Demonstrated that the well known voting
    techniques of ROVER and voting on lattices are instances of segmental MBR decoding,
    and developed their extensions.

Researcher, Jul 1997 - Aug 1997
    Workshop on Innovative Techniques for LVCSR; Syllable based speech recognition.

Teaching Assistant, Feb 1997 - May 1997 & Feb 1996 - May 1996
    Neuroengineering : A course on application of engineering ideas for diagnosis and
    treatment of neuropathologies.

Biomedical Instrumentation Laboratory, Johns Hopkins University

Research Assistant, Sep 1993 - Aug 1995
    LPC analysis and neuronal correlates of anomalies in electroencephalograms. Involved
    applied signal processing, instrumentation, and neuronal simulations and modeling.

Teaching Assistant, Feb 1995 - May 1995 & Sep 1994 - Dec 1994
    Biomedical Instrumentation : A course on instrumentation for medical applications.

    - Abel Wolman Fellowship, Johns Hopkins University (95-96).
    - Tuition fellowship, Johns Hopkins University (93-95).
    - Best outgoing undergraduate student in electrical engineering at Indian Institute of
        Technology Kanpur (IITK), 1993.
    - Proficiency award for best project work in electrical engineering, IITK, 1993.
    - The Tata Consultancy Services award for best software project at IITK, 1993.
    - Student member IEEE, ISCA.

Journal Articles:
    - Goel V. and Byrne W.J., ``Minimum Bayes-risk automatic speech recognition,''
        Computer Speech and Language, Vol. 14(2), pp.     115--135, 2000.
    - Goel V., Brambrink A.M., Baykal A., and Thakor N.V., ``Dominant frequency
        analysis reveals brain's response to injury and recovery,'' IEEE Transactions on
        Biomedical Engineering, Vol. 43(11), pp. 1083--1092, 1996.

Selected Conference and Workshop Papers:
    - Goel V. and Byrne W.J., ``Applications of Minimum Bayes-Risk Decoding to
        LVCSR,'' LVCSR Workshop, May 16-19, UMCP, College Park, MD, 2000.
    - Goel V. and Byrne W.J., ``Task dependent loss functions in speech recognition:
        A-star search over recognition lattices,'' Eurospeech-99, pp. 1243--1246,
        Budapest, Hungary, 1999.
    - Goel V. and Byrne W.J., ``Task dependent loss functions in speech recognition:
        Application to named entity extraction,'' ESCA ETRW Workshop on Accessing
        Information from Spoken Audio, pp. 49--53, Cambridge, UK, 1999.
    - Goel V., Byrne W.J., and Khudanpur S., ``LVCSR rescoring with modified loss
        functions: A decision theoretic perspective,'' ICASSP-98, May 9-12, 1998.
    - Ganapathiraju A., Goel V., Picone J., et.al., ``Syllable - A promising recognition
        unit for LVCSR,'' 1997 IEEE Workshop on Automatic Speech Recognition and
        Understanding, Dec 14-17, 1997.
    - Corrada A., Doddington G., Ganapathiraju A., Goel V., et.al., ``The syllable team,''
        HUB-5 Conversational Speech Recognition Workshop, Nov 4-6, 1997.
    - Goel V. and Thakor N.V., ``A model of excitotoxic injury to the hippocampal
        neurons,'' Neural Modeling of Cognitive and Brain Disorders, Jun 8-10, 1995.
    - Kong X., Goel V., and Thakor N.V., ``Quantification of injury-related EEG
        signal changes using Itakura distance measure,'' ICASSP-95, May 9-12, 1995.
    - Goel V., Brambrink A.M., Baykal A., and Thakor N.V., ``Autoregressive
        modeling of EEG reveals brain's response to injury,'' IEEE/EMBS Annual
        International Conference, Nov 3-6, 1994.
    - Goel V., Brambrink A.M., Baykal A., and Thakor N.V., ``Detection of
        hypoxic-asphyxic insult and recovery using autoregressive modeling of
        EEG signals,'' American EEG Society Annual Meeting, Sep 19-20, 1994.

    Programming Languages: C, C++, VisualBasic, Pascal.
    Scripting Languages: Perl, Awk.
    Toolkits: Matlab, HTK, AT&T FSM Tools.
    Operatring Systems: Unix, Windows98, WindowsNT.

    Indian citizen, at present on F-1 (student visa).

    Available upon request.