Keith W. Godin
Keith W. Godin earned the B.S. degree in Computer Engineering from Rose-Hulman Institute of Technology in Terre Haute, IN, USA in 2007, and the M.S. degree in Electrical Engineering from the University of Texas at Dallas in Richardson, TX, USA in 2009. He is currently a Ph.D. Candidate at the University of Texas at Dallas.

Since the fall of 2007 he has been a Research Assistant with the Center for Robust Speech Systems (CRSS) at the University of Texas at Dallas. During the spring and summer of 2006, he was a Technical Intern with Intel Corp. in Folsom, CA, where he worked in the Chipsets group on pre-silicon validation. During the summer of 2007, he was a Technical Intern with Science Applications Intl. Corp. (SAIC) in Jupiter, FL. During the summer of 2010, he worked as a Research Intern with Research Associates for Defense Conversion (RADC) in Rome, NY. During the summer of 2011, he was a Research Intern with Microsoft in Redmond, WA.

Mr. Godin's research interests include speech signal processing and speech analysis. He is a graduate student member of the IEEE and a student member of the Intl. Speech Communication Assoc. (ISCA).

Email: godin AT ieee DOT org
Linked In: www.linkedin.com/in/keithwgodin

Education

Ph.D. Candidate, Electrical Engineering
University of Texas at Dallas, Richardson, TX. Expected completion: May 2013.


Master of Science, Electrical Engineering, December 2009
University of Texas at Dallas, Richardson, TX. Thesis title: "Classification based analysis of speech under physical task stress".


Bachelor of Science, Computer Engineering, May 2007
With a minor in Economics. Rose-Hulman Institute of Technology, Terre Haute, IN.

Research Experience

Research Asssistant, University of Texas at Dallas, August 2007 - present

  • Developed and applied experimental technique to measure the effects of physical stress on speech
  • Developed and applied experimental technique to contrast the effects of short term and long term speaker variability on speech
  • Coded speaker recognition system using Perl, C++, and HTK
  • Developed 6000+ line C++ library for speaker recognition and speech classification


Research Intern, Microsoft, May - August 2011

  • Sound source localization


Research Intern, Research Associates for Defense Conversion (RADC) Inc., May - August 2010

  • Coded speaker variability compensation technique for speaker verification in C++

Industrial Experience

Engineering Intern Science Applications International Corp. (SAIC), June - August 2007

  • Implemented Huffman Coding in C for a TI DSP
  • Designed digital logic, and implemented on a Xilinx FPGA, for a serial data converter to connect satellite simulation hardware to a tester prototype


Engineering Intern Intel Corp., March - August 2006

  • Perl programming for automated test of digital logic


Engineering Intern Rose-Hulman Ventures, March - August 2005

  • Algorithm research and development, microcontroller programming, circuit board design, and cost projections for an embedded speech detection system

Publications

Relevant Coursework

  • Speech and Speaker Recognition: Speech recognition, acoustic phonetics, HMMs.
  • Signal Theory: Mathematics of signal processing: vector spaces, projections, signal modeling, SVD, EM algorithm.
  • Speech Science: Background and current literature in speech production, perception, and acoustic phonetics.
  • Speech Signal Processing: Speech coding, MMSE and spectral subtraction speech enhancement, pitch detection.
  • Machine Learning: Neural nets, support vector machines (SVM), Adaboost, PAC.
  • Detection and Estimation: Classical and Bayesian estimation techniques for random variables. CRLB, linear estimators, ML and MAP estimation.
  • Professional Activities

    Honors

    • Jonsson Distinguished Scholars Fellowship, University of Texas at Dallas, 2007-2010