Michael Carlin

Michael Carlin

Johns Hopkins University
3400 North Charles Street
Barton Hall 105
macarlin AT jhu DOT edu

I am a final year Ph.D. candidate in Electrical and Computer Engineering and a member of the Center for Language and Speech Processing, working under the guidance of Mounya Elhilali. I was previously supported by a Graduate Fellowship from the Human Language Technology Center of Excellence where I worked with Aren Jansen. From 2006 through 2008 I was with the Information Directorate of the Air Force Research Laboratory and worked on variety of speech signal processing problems. In the summer of 2009 I worked with the speech group of SCALE.

In the fall of 2009, I had the privilege of studying information theory with Prof. Frederick Jelinek.

In the summer of 2011, I spent the summer working with the HLT group at MIT Lincoln Laboratory with Nicolas Malyska and Thomas Quatieri.

In the summer of 2013, I participated in another SCALE, working with Alan McCree, Pascal Clark, and Aren Jansen.


Research Interests

I am interested generally in computational neuroscience, machine learning, and biologically inspired methods for speech and audio signal processing. Our work has explored how enforcing temporal stability in model thalamo-cortical neurons yields highly structured spectro-temporal receptive fields (STRFs) akin to those commonly observed in auditory physiology. We have also developed a computational model of task-driven auditory plasticity, demonstrating how a discriminative model can induce adaptive changes in STRFs akin to those seen in neurophysiological studies. Finally, we consider how such models can be used to generate noise-robust features for common speech tasks.


Refereed Publications and Conference Presentations

  • Carlin, M. A. and Elhilali, M. “Modeling attention-driven plasticity in auditory cortical receptive fields.” Submitted to PLoS Computational Biology.
  • Carlin, M. A. and Elhilali, M. “A computational model of optimal adaptive changes in auditory cortical receptive fields during behavioral tasks.” COSYNE Abstracts 2014, Salt Lake City, USA, 2014.
  • Carlin, M. A. and Elhilali, M. ”Sustained firing of model central auditory neurons yields a discriminative spectro-temporal representation for natural sounds.” PLoS Comp. Bio., 9(3), e1002982, 2013.
  • Carlin, M. A., Patil, K., Nemala, S. K., and Elhilali, M. ”Robust phoneme recognition using biomimetic speech contours.” In Proc. Interspeech, 2012.
  • Carlin, M. A., Malyska, N., and Quatieri, T. F. ”Speech enhancement using sparse convolutive non-negative matrix factorization with basis adaptation.” In Proc. Interspeech, 2012.
  • Carlin, M. A. and Elhilali, M. ”On the role of pitch in binding auditory streams.” InAbstracts of the 16th International Symposium on Hearing, 2012.
  • Carlin, M. A. and Elhilali, M. ”Sustained firing of model cortical neurons yields richly structured spectro-temporal receptive fields.” In Abstracts of the Thirty-fifth ARO Mid-winter meeting, Volume 35, Mt. Royal, NJ: Association for Research in Otolaryngology, 2012.
  • Carlin, M. A., Thomas, S., Jansen, A., and Hermansky, H. ”Rapid Evaluation of Speech Representations for Spoken Term Discovery.” In Proc. Interspeech, 2011.
  • Carlin, M. A. and Elhilali, M. ”Exploiting temporal coherence in speech for data-driven feature extraction.” In Proc. IEEE Conf. on Information Sciences and Systems, 2011.
  • Carlin, M. A. and Elhilali, M. ”Exploring the relationship between principles of temporal coherence and coding strategies in the auditory system.” In Abstracts of the Thirty-fourth ARO Mid-winter meeting, Volume 34, Mt. Royal, NJ: Association for Research in Otolaryngology, 2011.
  • Lawson, A., Linderman, M., Leonard, M., Stauffer, A., Pokines, B, and Carlin, M. A. ”Perturbation and Pitch Normalization as Enhancements to Speaker Recognition.” In Proc. ICASSP, 2009.
  • Carlin, M. A. ”Estimation of Target-to-Interferer Ratio using the Auditory Image Model.” Presented at Acoustics ’08, J. Acoust. Soc. Am., 2008.
  • Lawson, A., Carlin, M. A., Stauffer, A., and Linderman, M. ”Automatic Data Enhancement for Language Identification using STRAIGHT Voice Generation.” Presented at Acoustics ’08, J. Acoust. Soc. Am., 2008.
  • Carlin, M. A., Smolenski, B. Y. ”Detection of Speaker Change Points in Conversational Speech.” In Proc. IEEE Aerospace Conference, 2007.
  • Carlin, M. A., Smolenski, B. Y., and Wenndt, S. J. ”Unsupervised Detection of Whispered Speech in the Presence of Normal Phonation.” In Proc. Interspeech, 2006.

© Michael Carlin, 2015. All rights reserved.

Johns Hopkins University

Johns Hopkins University, Whiting School of Engineering

Center for Language and Speech Processing
Hackerman 226
3400 North Charles Street, Baltimore, MD 21218-2608

Center for Language and Speech Processing