Michael Scordilis

Photo of Michael Scordilis

Michael Scordilis

Associate Professor in Practice | College of Engineering | Electrical & Computer Engineering Department
Work Phone: (305) 284-3323/4044

Website: Digital Audio and Speech Processing Lab
Resume
Intranet

Research Interests

Signal Processing for Speech, Audio & Music Signal Recovery & Enhancement, Psychoacoustics, Language Processing, and Multimedia Signal Processing

HIGHER EDUCATION

    • Clemson University, Clemson, South Carolina, Ph.D. in Electrical Engineering. (1990)
    • Clemson University, Clemson, South Carolina, M.S. in Electrical Engineering. (1986)
    • Royal Melbourne Institute of Technology, Melbourne, Australia, Other in Communication Engineering. (1983)

EXPERIENCE

    • University of Miami, Associate Professor. Department of Electrical & Computer Engineering (2012 - Present)
    • The University of Patras, Visiting Professor. Department of Electrical and Computer Engineering (2000)
    • The University of Patras, Visiting Professor. Department of Electrical and Computer Engineering (1999)
    • University of Patras, Greece, Senior Researcher. Department of Electrical and Computer Engineering (1995 - 1997)
    • University of Melbourne, University Lecturer (Tenured). Department of Electrical and Electronic Engineering (1990 - 1995)
    • Sun Microsystems Laboratories, Visiting Senior Scientist. Speech Recognition Group (1994)
    • Bell Communications Research (Bellcore), Visiting Senior Scientist. Speech Analysis and Synthesis Group (1994)
    • Clemson University, Research Fellow and Teaching Assistant. Department of Electrical and Computer Engineering (1984 - 1990)

PUBLICATIONS

  • Juried or Refereed Journal Articles or Exhibitions

    • Iliev, A. I., Scordilis, M. S., Papa, J. P., FalcÌ£o, A. X. (2010).Spoken emotion recognition through optimum-path forest classification using glottal features. Academic Press, Journal of Computer Speech and Language - Special Issue on Emergent Artificial Intelligence Approaches for Pattern Recognition in Speech and Language Processing, Volume 24, 445-460.
    • Iliev, A. I., Michael, S. S., Scordilis, M. S. (2010).Spoken Emotion Recognition using Glottal Symmetry. EURASIP Journal on Advances in Signal Processing ‰ÛÒ Special Issue on Emotion and Mental State Recognition from Speech, accepted for publication.
    • Jin, W., Liu, X., Scordilis, M. S., Han, L. (2010).Speech Enhancement Using Harmonic Emphasis and Adaptive Comb Filtering. IEEE Transactions on Audio, Speech and Language Processing, Volume 18 (2), 356-368.
    • Zhang, Y., Scordilis, M. S. (2008).Effective Online Adaptation of Gaussian Mixture Models and its Application to Speech Classification. Elsevier Pattern Recognition Letters; Addendum to the Special Issue on Advances in Pattern Recognition for Speech and Audio Processing, 29, 735-744.
    • He, X., Scordilis, M. S. (2008).Efficiently Synchronized Spread Spectrum Audio Watermarking. Research Letters in Signal Processing; Article ID 251868, 5 pages.
    • He, X., Scordilis, M. S. (2008).Psychoacoustic Music Analysis Based on the Discrete Wavelet Packet Transform. Research Letters in Signal Processing; Article ID 346767, 5 pages.
    • He, X., Scordilis, M. S. (2006).A Psychoacoustic Model Based on the Discrete Wavelet Packet Transform?,. Elsevier, Journal of the Franklin Institute, 34 (7), 738-755.
    • He, X., Scordilis, M. S. (2006).Speech Enhancement by Residual Domain Constrained Optimization. Elsevier Journal of Speech Communication, 8 (10), 1349-1364.
    • Jin, W., Scordilis, M. S. (2006).Speech Enhancement by Residual Domain Constrained Optimization. Elsevier Speech Communication, 48 (10), 1349-1364.
    • Abdou, S., Scordilis, M. S. (2004).Beam Search Pruning in Speech Recognition Using a Posterior Probability-Based Confidence Measure. Elsevier Journal of Speech Communication, 42 (3-4), 409-428.
    • Veprek, P., Scordilis, M. S. (2002).Analysis, Enhancement and Evaluation of Five Pitch Determination Techniques. Elsevier Speech Communication, 37 (3-4), 249-270.
    • Grayden, D. B., Scordilis, M. S. (1996).Phoneme Recognition in Fluent Speech using Time-Delay and Fully Interconnected Neural Networks: A Comparison. Australian Journal of Intelligent Information Processing Systems, 3 (3), 8-May.
    • Scordilis, M. S. (1996).A neuronal formant synthesizer. Journal of Mathematics and Computers in Simulation, Special Issue on "Neural Networks/ Neurocomputing, 40 (5-6), 615-622.
    • Scordilis, M. S., Gowdy, J. N. (1995).A Neural Network-based Control Strategy for a Speech Formant Synthesizer. Journal of Artificial Neural Networks, 2 (3), 195-203.
    • Scordilis, M. S. (1995).Current Speech Technology and the Need for Robust Processing. Australian Speech Science and Technology Association Bulletin, 12, 4-Mar.
  • Book Chapters

    • Zhang, Y., Scordilis, M. S. (2008). Online Acoustic and Pronunciation Adaptation Techniques in Automatic Speech Recognition. (pp. ). Nova Science Publishers.
    • Scordilis, M. S., He, X. (2007). Spread Spectrum for Digital Audio Watermarking. (pp. Nov-49). Information Science Reference.
    • Scordilis, M. S. (1991). A Neural Network Cluster for the Control of a Speech Synthesizer. (pp. 229-235). Kluwer Academic Publishers.

 

Translate »