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
- Keith W. Godin and John H. L. Hansen (accepted), "Analysis of the effects of physical task stress on the speech signal", J. of the Acoustical Soc. of Am.
- Keith W. Godin and John H. L. Hansen (2011), "Vowel context and speaker interactions influencing glottal open quotient and formant frequency shifts in physical task stress", Interspeech 2011, pp. 2945-2948, Florence, Italy, August.
- Xing Fan, Keith W. Godin, and John H. L. Hansen (2011), "Acoustic analysis of whispered speech for phoneme and speaker dependency", Interspeech 2011, pp. 181-184, Florence, Italy, August.
- Keith W. Godin and John H. L. Hansen (2010), "Session Variability Contrasts in the MARP Corpus", Interspeech 2010, pp. 298-301, Makuhari, Japan, Sep.
- Keith W. Godin (2009), "Classification based analysis of speech under physical task stress", Master's Thesis, University of Texas at Dallas, Richardson, TX, Dec.
- Keith W. Godin and John H. L. Hansen (2008), "Analysis and Perception of Speech Under Physical Task Stress", Interspeech 2008, pp. 1674-1677, Brisbane, Australia, Sep.
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.
- Engineer Intern, Texas (EIT)
- Graduate Student Member IEEE
- Student Member Intl. Speech Communication Assoc. (ISCA)
- Jonsson Distinguished Scholars Fellowship, University of Texas at Dallas, 2007-2010