BIOGRAPHICAL SKETCH
CLEMENTS, MARK A. - Professor
School of Electrical and Computer Engineering
Georgia Institute of Technology
Atlanta, Georgia 30332-0250
EDUCATIONAL BACKGROUND
EMPLOYMENT HISTORY
- Massachusetts Institute of Technology
Graduate Teaching Assistant 1976-1978
National Institutes of Health Trainee 1979-1981
Graduate Research Assistant 1981-1982
-
Verbex Corporation
Research Associate (Part-time) 1979-1981
-
Georgia Institute of Technology
Assistant Professor 1982 - 1988
Associate Professor 1988 - 1993
Professor 1993-present
Director, Interactive Media Technology Center , 2000-present
EXPERIENCE SUMMARY
Dr. Clements has taught graduate
and undergraduate courses in probability and speech and signal processing,
pattern recognition, and random processes. He was technical program
co-chairman of Speech Tech '86 and Technical Program Chair of
ICASSP '96. He has served a member of the IEEE speech
technical committee. He was an associate editor of speech
processing for IEEE Trans. on Acoustics, Speech, and Signal Processing.
He has been principal investigator on numerous sponsored
research projects concerned with speech processing.
His present consulting concerns automatic speech recognition and digital
speech coding.
CURRENT FIELDS OF INTEREST
Digital speech processing and analysis, speech recognition,
analysis and compensation of stress in speech,
sensory aids for the hearing impaired, pattern recognition, digital signal
processing.
AWARDS AND PROFESSIONAL ACTIVITIES
- Supervised Investors Award for Best Teacher in Electrical
Engineering, MIT - 1979
-
Technical Program Co-Chairman, SpeechTech '86 - 1986
-
Sigma Xi Doctoral Thesis Advisor Award, Georgia Tech - 1988, 1991, and 1997.
-
Sigma Xi Undergraduate Research Advisor Award, Georgia Tech - 1989
-
Senior Member IEEE
-
Member ASA
-
IEEE Speech Technical Committee, 1987-1991
-
IEEE Acoustics, Speech and Signal Processing, Associate Editor, 1989-1991
-
Technical Program Chairman, ICASSP-96.
PATENTS
- ``Apparatus and Method for Modifying a Speech Waveform
to Compensate for Recruitment of Loudness,'' Patent number 5,274,711,
Granted: December 27, 1993.
- ``Singing Voice Synthesis,'' with E. George, M. Macon,
L. Jensen-Link, J. Oliverio, Patent number 6,304,846,
Granted: October 16, 2001.
- "High Speed Wordspotting for Audio Archive Retrieval,"Peter Cardillo, Mark Clements, Ed Price, provisional patent filed March 4, 2000;
full filing, March 2001.
SELECTED PUBLICATIONS
Theses
- M. A. Clements, ``An Evaluation of Two Tactile Speech
displays,'' S.M. Thesis, M.I.T., September 1978.
- M. A. Clements, ``A Comparative Evaluation of Different Signal
Processing Techniques for Communication of Speech Through the Tactile
Sense,'' Sc.D. Thesis, M.I.T., January 1982.
Books
- S. R. Quackenbush, T. P. Barnwell, and M. A. Clements,
Objective Measures for Speech Quality Testing, Prentice-Hall,
Englewood Cliffs, NJ 1988.
- Digital Signal Acquisition and Representation,
Chapter 2
in Animal Acoustic Communications, S. Hopp, (ed.)
Springer-Verlag, 1998.
- M. A. Clements, ``Automatic Recognition of Speech
in Stress,'' U.S. Army Human Engineering Laboratory Printing Office,
Aberdeen Proving Ground, Maryland, 67 page research monograph, 1991.
- G. Miao and M. Clements,
Digital Signal Processing and Statistical Pattern Recognition , Marcel Dekker, June 2002.
Journal Publications
- M. Clements, D. Mook, N. Durlach, and L. Braida,
``Experiments with Optacon-Based Speech Displays,'' Speech Communication
Papers of the Acoustic Society of America, June 1979.
- J. Snyder, M. Clements, C. Reed, N. Durlach, L. Braida, ``Tactile
Communication of Speech, Part I: Comparison of Tadoma and Frequency-Amplitude
Spectral Display in a Consonant Discrimination Task,''
J. Acoust. Soc. Am., 71, pp. 1249-1254, 1982.
- M. Clements, L. Braida, and N. Durlach, ``Comparison of Two
Tactile Speech Codes," J. Acoust. Soc. Am., 71, S59, 1982.
- M. Clements, N. Durlach, L. Braida, ``Tactile Communication
of Speech Part II: Comparison of Two Spectral Displays in a Vowel
Discrimination Task,'' J. Acoust. Soc. Am., 72, pp. 1131-1135,
1982.
- M. H. Hayes and M. A. Clements, ``An Iterative Approach to
Pisarenko's Harmonic Decomposition,'' IEEE Trans. on Acoust.,
Speech, and Signal Processing, 34, pp. 485-492, June 1986.
- M. H. Hayes, M. A. Clements, and D. M. Wilkes,
``Iterative Harmonic Decomposition of Non-Stationary Random Processes:
Theory and Application to Spectral Line Tracking,'' Mathematics in Signal
Processing, T. S. Durrani et al., Editors, pp. 105-119, Clarendon
Press, Oxford, England, 1987.
- M. A. Clements, ``Voice Recognition Systems can be Designed to
Serve a Variety of Purposes,'' Industrial Engineering, 19,
44-57, Sept. 1987.
- M. A. Clements and S. H. Isabelle, ``Reconstruction of a
Positive Definite Toeplitz Matrix from Its Sequence of Minimum Eigenvalues,''
IEEE Trans. on Acoust., Speech, and Signal Processing, vol. ASSP-36,
pp. 1784-86, November 1988.
- M. A. Clements and J. Pease, ``On Causal Linear Phase IIR Digital
Filter,'' IEEE Trans. on Acoust., Speech, and Signal Processing,
April 1989.
- M. A. Clements, L. D. Braida, and N. I. Durlach, ``Tactile
Communication of Speech: III. Quantitative Evaluation of a Computer-Based
Tactile Speech Display,'' Journal of Rehabilitative Engineering,
May 1989.
- D. J. Pepper, T. P. Barnwell, and M. A. Clements, ``Using a
Ring Parallel Processor for Hidden Markov Model Training,'' IEEE
Trans. on Acoust., Speech, and Signal Processing, Feb. 1990.
- D. J. Pepper and M. A. Clements, ``Phonetic Recognition Using a
Large Hidden Markov Model,'' IEEE Trans. on Acoustics, Speech, and
Signal Processing, June 1992.
- J. H. Hansen and M. A. Clements, ``Constrained Iterative Speech
Enhancement,'' IEEE Trans. on Acoust., Speech, and
Signal Processing, Feb. 1991.
- B. Carlson and M. Clements, ``A Computationally Compact
Divergence Measure for Speech Processing,''
IEEE Trans. on Pattern Analysis and Machine Intelligence,
Dec. 1992, pp. 1255-1260.
- B. Carlson and M. Clements, ``A Projection-Based
Likelihood Measure for Speech Recognition in Noise,'' IEEE
Trans. on Speech and Audio Processing, Jan. 1994, pp. 97-102.
- S. Lim and M. Clements, ``Pseudo-Continuous Hidden
Markov Modeling for Automatic Speech Recognition,'' Proc. IEEE
Southeastcon, refereed, 7 pages, Birmingham, AL, April 12-15, 1992.
- K. E. Cummings and M. A. Clements, ``Glottal Models for
Digital Speech Processing: A Historical Review and New Results,''
Digital Signal Processing: A Review Journal, Vol. 5, No. 1,
pp. 21-42, January 1995. (invited)
- R. Cole, L. Hirschman, et al. (including
M. Clements), ``the Challenge of Spoken Language
Systems: Research Directions for the Nineties,'' IEEE
Trans. on Speech and Audio Processing, Vol. 3, No. 1, pp. 1-21,
January 1995.
- K. Cummings, J. Maloney, and M. Clements, ``Application
of Yee's Finite Difference Method to Modelling Acoustic Wave
Propagation in the Vocal Tract,'' Journal of the
Acoustical Society of America, March 1995.
- K. Cummings and M. Clements, ``Analysis of the Glottal
Excitation of Emotionally Stressed Speech,'' Journal of the
Acoustical Society of America, July 1995, pp. 88-99.
- J. Hansen and M. Clements, ``Source Generation
Equalization and Enhancement of Spectral Properties for Robust Speech
Recognition in Noise and Stress,'' IEEE Trans. of
Speech and Audio Processing, Sept. 1995, pp. 407-415.
- M. Macon and M. Clements, ``Sinusoidal Modeling and
Modification of Unvoiced Speech,'' IEEE
Trans. on Speech and Audio, Nov. 1997, pp. 557-560.
- J. Miao and M. Clements, ``High-Speed Digital Waveform
Classification Using 2-D Principal Projection Spatial Filter,''
submitted to IEEE Transactions on Signal Processing.
- J. Miao and M. Clements, ``On Canonical Discriminant
Transform with Gaussian Spatial Filter for Digital Waveform
Recognition,'' submitted to IEEE Signal Processing Letters.
- J. Miao and M. Clements, ``Comparison Studies of 2-D
Transform Features Based Unsupervised Pattern Recognition for
Digital Pulse Waveform
Classification,'' submitted to IEEE Transactions on Pattern
Analysis and Machine Intelligence.
- Miao, Jianwei, and Clements, Mark, ``Canonical
Discriminant Transform and its Application
in Digital Waveform Classification,'' submitted to IEEE
Transactions on Signal Processing,
- M. W. Macon and M.A. Clements, "Waveform models for data-driven speech
synthesis,"
Journal of the Acoustical Society of America , Vol. 105, No. 2, Pt.2, p. 1031,
February 1999.
- T. R. Trinkaus and M. A. Clements, "An Algorithm for Compression of
Wideband Diverse Speech and Audio Signals," submitted to IEEE Transactions on
Speech and Audio Processing.
- David V. Anderson and Mark A. Clements, "Multi-resolution Sinusoidal Modeling,"
submitted to IEEE Transactions on Speech and Audio Processing.
- R. Morris and M. Clements, "Modification of Formants in the Line Spectrum
Domain, " IEEE Signal Processing Letters , vol 9, pp 19-21
January 2002.
-
Cardillo, P. Clements, M., Miller, M., "Phonetic Searching vs
Large Vocabulary Continuous Speech Recognition," International
Journal of Speech Technology , pp 9-22, January 2002.
- Robert Morris and Mark Clements, "Reconstruction of Speech from
Whispers," accepted for publication,
International Journal of Medical Engineering and Physics , June 2002.
-
Xiaozheng Zhang, Charles C. Broun, Russell M. Mersereau,
Mark A. Clements, "Automatic Speechreading with Applications to Human-Computer Interfaces," accepted to
EURASIP JASP special issue on Joint Audio-Visual Speech Processing.
Conference Presentations with Proceedings
- M. Clements, L. Braida, N. Durlach, ``Quantitative Methods
for the Comparative Evaluation of Artificial Tactile Speech Displays,''
Proceedings of 1983 Int'l Conference IEEE Engineering in
Medicine and Biology Society, Philadelphia, PA, September 1982. (Invited).
- M. A. Clements, ``Processing of Speech for Tactile Communication,''
Proceedings of Southeastern Symposium on System Theory,
Huntsville, AL, March 1983. (Invited).
- M. Clements, L. Braida, N. Durlach, ``Speech Processing for
Artificial Tactile Speech Displays,'' Proceedings of 1983
IEEE Int. Conf. on Acoust., Speech, and Signal Processing, Boston, MA,
April 1983.
- M. A. Clements and R. C. Rose, ``Linear Predictive Modeling with
a Maximally Pulse-like Residual,'' Proc. IEEE ASSP Workshop on
DSP, Cape Cod, 1984.
- H. A. Hawkins, D. M. Wilkes, M. A. Clements, and M. H. Hayes,
``Perceptual Weightings and Optimal Pulse-Positioning in Multipulse LPC
Coding,'' Proceedings of 1985 IEEE Int. Conference on
Acoust., Speech, and Signal Processing, Tampa, FL, March 1985.
- R. C. Rose, M. A. Clements, ``All-Pole Speech Modeling
with a Maximally Pulse-Like Residual,'' Proceedings of 1985
IEEE Int. Conf. on Acoust., Speech, and Signal Processing, Tampa, FL,
March 1985.
- M. H. Hayes, M. A. Clements, and D. M. Wilkes, ``Iterative
Harmonic Decomposition of Non-Stationary Random Processes: Theory and
Application to Spectral Line Tracking,'' Proceedings
Mathematics in Signal Processing Conference, Bath, England, Sept. 1985.
- E. Farges and M. Clements, ``Hidden Markov Models Applied to
Very Low Bit Rate Coding,'' Proceedings of 1986 IEEE
Int. Conference on Acoust., Speech, and Signal Processing, Tokyo, Japan,
April 1986.
- D. J. Healy and M. A. Clements, ``Toward the Goal of Video-Deaf
Communication over Public Telephone Lines,'' Proceedings of SPIE:
Visual Communication and Image Processing, Vol. 77, pp. 83-90, Cambridge,
MA, Sept. 1986.
- M. A. Clements and S. Lim, ``Hidden Markov Model Speech
Recognition Based on Kalman Filtering,'' Proceedings of IEEE
Int. Conf. on Acoust., Speech, and Signal Processing, Dallas, TX, April 1987.
- J. H. Hansen and M. A. Clements, ``Iterative Speech Enhancement
with Spectral Constraints,'' Proceedings of IEEE Int. Conf. on
Acoust., Speech, and Signal Processing, Dallas, TX, April 1987.
- E. P. Farges and M. A. Clements, ``An Analysis/Synthesis Hidden
Markov Model of Speech,'' Proceedings 1988 IEEE Int. Conf. on
Acoust., Speech, and Signal Processing, New York, April 1988.
- J. H. Hansen and M. A. Clements, ``Constrained Iterative Speech
Enhancement with Application to Automatic Recognition,'' Proceedings
1988 IEEE Int. Conf. on Acoust., Speech, and Signal Processing, New York,
April 1988.
- K. Cummings, M. Clements, and J. Hansen, ``Estimation and
Comparison of the Glottal Source Waveform Across Stress Styles Using
Glottal Inverse Filtering,'' Proc. IEEE Southeastcon,
Columbia, SC, pp. 776-781, April 1989.
- J. Hansen and M. Clements, ``Stress Compensation and
Noise Reduction Algorithms for Robust Speech Recognition,''
Proc. 1989 International Conf. on Acoustics, Speech, and Signal
Processing, vol. S1, pp. 266-269, May 1989.
- J. Hansen and M. Clements, ``Use of Objective Speech Quality
Measures in Selected Effective Spectral Estimation Techniques for Speech
Enhancement,'' Proc. Midwest Symposium on Circuits and Systems,
Urbana-Champaign, IL, August 1989.
- B. Carlson and M. Clements, ``A Weighted Projection Measure for
Robust Speech Recognition,'' Proc. IEEE Southeastcon, New Orleans, LA,
April 1990.
- K. Cummings and M. Clements, ``Analysis of Glottal Waveforms
Across Stress Styles,'' Proc. of IEEE Int. Conf. on Acoustics, Speech,
and Signal Processing, Albuquerque, NM, April 1990.
- B. Carlson and M. Clements, ``Application of a Weighted
Projection Measure for Robust Hidden Markov Model Based Speech Recognition,''
Proceedings of IEEE Int. Conf. on Acoustics, Speech, and Signal
Processing, May 1991.
- D. Pepper and M. Clements, ``On the Phonetic Structure of a
Large Hidden Markov Model,'' Proceedings of IEEE Int. Conf. on
Acoustics, Speech, and Signal Processing, May 1991.
- J. Rutledge and M. Clements, ``Time-Varying Frequency-Dependent
Compensation for Recruitment of Loudness,'' Proc. of IEEE Int. Conf. on
Acoustics, Speech, and Signal Processing, Toronto, Canada, May 1991.
- K. E. Cummings and M. A. Clements, ``Improvements to and
Applications of Analysis of Stressed Speech Using Glottal Waveforms,''
Proc. of IEEE Int. Conf. on Acoustics, Speech, and Signal Processing,
San Francisco, CA, March 23-26, 1992.
- B. A. Carlson and M. A. Clements, ``A Weighted
Projection Measure for Mixture Density HMM Based Recognition in Noise,''
Proc. of IEEE Int. Conf. on Acoustics, Speech, and Signal Processing,
San Francisco, CA, March 23-26, 1992.
- K. Cummings and M. A. Clements, ``Application of the
Analysis of Glottal Excitation of Stressed Speech to Speaking Style
Modification,'' Proc. of IEEE Int. Conf. on Acoustics, Speech,
and Signal Processing, Minneapolis, MN, April 27-30, 1993.
- K. Cummings, M. Clements, and J. Maloney, ``A
Finite-Difference Time Domain Model of Speech Production,''
Proc., First International Conf. on Neural, Parallel, and Scientific
Computing, May 1995, Atlanta, GA (6 pages), invited.
- D. Lambert, K. Cummings, J. Rutledge, and M. Clements,
``Synthesizing Styled Speech Using the Klatt Synthesizer,''
Proc. of the IEEE International Conference on Acoustics, Speech,
and Signal Processing, Detroit, MI, May 1995.
- K. Cummings and M. Clements, ``Modelling Speech
Production Using Yee's Finite Difference Method,''
Proc. of the IEEE International Conference on Acoustics, Speech,
and Signal Processing, Detroit, MI, May 1995.
- J. Miao and M. Clements, ``Unsupervised Pattern Recognition
for Digital Waveform Classificaiton from Radiation Detectors,''
Proc. of the IEEE International Conference on Acoustics, Speech,
and Signal Processing, Detroit, MI, May 1995.
- M. W. Macon and M. A. Clements, ``Speech Concatenation and
Synthesis Using an Overlap-Add Sinusoidal Model,''
Proc. ICASSP'96, Vol.I, pp. 361-364, Atlanta, GA, 1996.
- B. F. Necioglu, M. A. Clements, T. P. Barnwell III,
``Objectively
Measured Descriptors Applied To Speaker Characterization,''
Proc. ICASSP'96, Vol.I, pp. 483-486, Atlanta, GA, 1996.
- J. Miao, M. A. Clements, ``Optimal Discriminant Feature-Based
Waveform Recognition With Neural Networks,"
Proc. ICASSP'96, Vol.I, pp. 3462-3466, Atlanta, GA, 1996.
- J. Miao, M. A. Clements, ``Canonical Discriminant
Feature-Based Digital Waveform Recognition with Neural
Networks,"
Proc. International Conference on Signal Processing Applications
and Technology, Boston, MA, October 1996.
- B. F. Necioglu, M. A. Clements, T. P. Barnwell III,
``Reliability Assessment and Evaluation of Objectively
Measured Descriptors for Speaker Characterization,''
Proc. ICASSP'97, Vol.II, pp. 995-999, Munich, Germany, 1997.
- M. W. Macon, L. Jensen-Link, J. Oliverio, M. A. Clements, and E. B.
George, ``A Singing
Voice Synthesis System Based on Sinusoidal Modeling,"
Proc. ICASSP'97, Vol.I, pp. 435-439, Munich, Germany, 1997.
- T. Unno, T. Barnwell. and M. Clements, ``The Multi-Modal
Multipulse Excitation Vocoder,''
Proc. ICASSP'97, Vol.III, pp. 1683-1687, Munich, Germany, 1997.
- M. W. Macon, L. Jensen-Link, J. Oliverio, M. A. Clements, and E. B.
George, ``Concatenation-based MIDI-to-Singing Voice Synthesis,''
103rd AES Convention, New York, 1997 September 26-29
- P. Frazier, P. Cardillo, J. Kalter, and M. Clements, ``Speech
Recognition Applied to Medical Transcription,'' Proceedings
of the 16th Annual International Voice Technologies Applications
Conference , pp. 197-206, September 9-11, 1997.
- N. Karaca, M. Clements, H. Gecim,``Speech Recognition under
Adverse Environments - RASTA Filtering and the Weighted Projection
Measure,'' IEEE Nordic Processing Symposium, June 8-11, 1998, Denmark.
- N. Karaca, M. Clements, H. Gecim, ``Turkish Speech Recognition under Noisy Environments - RASTA Processing and the
Weighted Projection
Measure,'' Signal Processing Applications
Conference, May 28-30, 1998, Ankara, Turkey.
- C. Nilubol, Q.H. Pham, R.M. Mersereau, M.J.T. Smith, M.A. Clements,
``Hidden Markov Modeling for SAR Automatic
Target Recognition,'' Proc. of ICASSP98, vol. 1, pp. 1061-1064, May 1998.
- C. Nilubol, Q.H. Pham, R.M. Mersereau, M.J.T. Smith, M.A. Clements ,
``Translational and rotational invariant hidden Markov model for
automatic target recognition," Proc. of SPIE, vol. 3357 pp. 179-185, 1998.
- B. F. Necioglu, M. A. Clements, T. P. Barnwell III, and A. Schmidt-Nielsen,
``Perceptual Relevance of Objectively Measured Descriptors for Speaker
Characterization," Proceedings of the IEEE International Conference on
Acoustics, Speech, and Signal Processing, Vol. II, pp. 869-872, Seattle,
Washington, May 1998.
- David V Anderson, Mark A Clements, ``Audio Signal Noise Reduction Using Mu
lti-resolution Sinusoidal Modeling,'' Proceedings of the IEEE International
Conference on
Acoustics, Speech, and Signal Processing, vol. 2, pp. 805-808,
Phoenix, March 1999.
- Trevor R Trinkaus and Mark A Clements, ``An Algorithm
for Compression of Diverse Speech and Audio Signals,''
Proceedings of the IEEE International Conference on
Acoustics, Speech, and Signal Processing, vol. 2, pp. 901-904,
Phoenix, March 1999.
- M. W. Macon, and M. A. Clements, ``An Enhanced ABS/OLA
Sinusoidal Model for Waveform Synthesis in TTS,:"
Proc. EUROSPEECH '99, Vol.5, pp. 2327-2330, Berlin, Germany,
Sept. 1999.
- N. Karaca, M. Clements, H. Gecim, ``Turkish Speech Recognition under Noisy Environments - Multiresolution Sinusoidal Transform,
Wiener Filtering, and Spectral Subtraction,'' Proc. 7th
Signal Processing Applications
Conference, June 17-19, 1999, Ankara, Turkey.
- B. F. Necioglu, M. A. Clements, and T. P. Barnwell III,
``Unsupervised Estimation of the Human Vocal Tract Length Over
Sentence Level Utterances," Proceedings of the IEEE International Conference on
Acoustics, Speech, and Signal Processing, Istanbul, Turkey, June
2000.
- "Efficient Multi-resolution Sinusoidal Modeling," David V. Anderson and Mark A.
Clements
World Conference on Systemics, Cybernetics, and Informatics,
July 23-26, 2000 Orlando, FL
Vol 6, pp 424-429, (invited).
-
Clements, M., Cardillo, P., Miller, M., "Phonetic Searching vs
Large Vocabulary Continuous Speech Recognition: How to Find What
You Really Want in Audio Archives," Proceedings, Conference of
Applied Voice Input/Output Society , San Jose, CA, April 2001.
(Named best paper at conference.)
-
Clements, M., Cardillo, P., Miller, M., "Phonetic Searching
of Digital Audio," Proceedings, 2001 Conference of the
National Association of Broadcasters , Las Vegas, April 2001.
- Robert Morris and Mark Clements, "Maximum Likelihood Compensation of
Zero-Memory Nonlinearities in Speech Signals," Proceedings, IEEE International Conference on
Acoustics, Speech, and Signal Processing , Salt Lake City, Utah, 2001.
- Robert Morris and Mark Clements, "Reconstruction of Speech from Whispers," Proceedings 2nd International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications,
13-15 September 2001, Firenze, Italy.
- Adriane Durey and Mark Clements, "Melody Spotting Using Hidden
Markov Models," Proceedings,
International Symposium on Music Information Retrieval,
October 15-17, 2001, Bloomington, IN.
-
C. C. Broun
X. Zhang, R. M. Mersereau, M. Clements,
"Automatic Speechreading with Application to Speaker Verification,"
Proceedings, IEEE Int. Conf. on Acoustics Speech and Signal
Processing , Orlando, Florida, May 2002.
-
Adriane Swalm Durey and Mark A. Clements, "Features for Melody Spotting Using Hidden Markov Models," Proceedings, IEEE Int. Conf. on Acoustics Speech and Signal
Processing , Orlando, Florida, May 2002.
- Zhang, R. M. Mersereau, M. Clements
C. C. Broun, "Visual Speech Feature Extraction for Improved
Speech Recognition," Proceedings, IEEE Int. Conf. on Acoustics Speech and Signal
Processing , Orlando, Florida, May 2002.
- R. W. Morris, M. A. Clements, "Estimation of Speech Spectra from Whispers,
Proceedings, IEEE Int. Conf. on Acoustics Speech and Signal Processing", Orlando,
Florida, May 2002.
- R. W. Morris, M. A. Clements, and J. S. Collura "Autoregressive Parameter Estimation of Speech in Noise,"
accepted to 2002 IEEE Speech Coding Workshop.
- Zhong, X, Arrowood, J., Clements, M., "Speech Coding and Transmission for Improved Automatic Recognition"
accepted to ICSLP 2002, Boulder CO USA, Sept 16-20, 2002.
- Arrowood, J., Clements, M., "Using Observation Uncertainty
in HMM Decoding,"
accepted to ICSLP 2002, Boulder CO USA, Sept 16-20, 2002.
-
Xiaozheng Zhang, Russell M. Mersereau, Mark Clements, "Bimodal Fusion in Audio-Visual Speech Recognition," accepted to IEEE Int. Conf. on
Image Processsing, Sept 22-25, 2002, Rochester, NY.
-
J. Arrowood and M. Clements, "HMM Decoding in Noisy Environments Using Uncertain Observations," accepted to Proc. Signal and Image Processing, Kauai, HI, August 2002.
Other Presentations
- M. A. Clements, L. D. Braida, N. I. Durlach,
``Comparison of Two Tactile Speech Codes,'' Spring 1982 Meeting of the
Acoust. Soc. Am., Chicago, IL, April 1982.
- M. A. Clements, ``Objective Speech Quality Measures Based
on Human Audition,'' Spring 1984 Meeting of the Acoust. Soc. Am., Norfolk, VA,
May 1984.
- J. H. Hansen and M. A. Clements, ``Objective Quality Measures
Applied to Enhanced Speech,'' Meeting of the Acoustical Society of America,
Nashville, TN, Fall, 1985.
- M. A. Clements and S. Lim, ``A Continuous-Trial Hidden Markov
Model for Speech Recognition,'' Speech Research Symposium V,
Baltimore, MD, February 19-20, 1987. (invited)
- M. A. Clements and E. P. Farges, ``A Global Hidden Markov Model
for Continuous Speech,'' Speech Research Symposium VI, Murray
Hill, NJ, November 5-6, 1987. (invited)
- J. H. Hansen and M. A. Clements, ``Evaluation of Speech Under
Stress and Emotional Conditions,'' Fall 1987 Meeting
of Acoust. Soc. Am., Miami, FL, November 1987.
- J. L. Lias and M. A. Clements, ``Sinusoidal Modeling of
Speech: Its Use in Simulating and Compensation for Recruitment of Loudness,''
Fall 1987 Meeting of Acoust. Soc. Am., Miami, FL,
November 1987.
- J. Rutledge, and M. Clements, ``Time Varying/Frequency
Varying Amplitude Compressions in Compensation for Recruitment of
Loudness,'' Fall 1988 Meeting of the Acoustical Society of America,
Honolulu, HI, November 1988.
- M. A. Clements, ``Subjective Assessment of Acoustic Patterns,''
Proc. of National Academy of Science Workshop on the Quality of
Digitally Processed Acoustic Signals, Mystic, Conn., April 1990. (invited)
- M. A. Clements, ``Robust Automatic Speech Recognition,''
NSF Workshop on Speech and Natural Language, Washington, D.C.,
February 1992. (invited)
- D. Lambert, K. Cummings, J. Rutledge, and M. Clements,
``Synthesizing Multistyle Speech Using the Klatt Synthesizer,''
Proc. of the 127th Meeting of the Acoustical Society of America,
Boston, Ma, June 1994.
- K. Cummings and M. Clements, ``Modelling Speech
Production Using Finite Difference Techniques,'' Proc. of the
127th Meeting of the Acoustical Society of America, Boston, Ma, June
1994.
- M. Macon and M. Clements, ``Speech Synthesis Based on an
Overlap-Sinusoidal Model,'' Proc. of the 129th Meeting of the
Acoustical Society of America, Washington, DC, June 1995.
- David V. Anderson and Mark A. Clements, ``Noise Suppression in Speech
Using Multi-resolution Sinusoidal Modeling," presented at the Fall 1998
Meeting of the Acoustical Society of America, Norfolk, VA.
- David V. Anderson and Mark A. Clements, ``Robust Speech Communications in
Noisy Systems and Environments," presentation at GCATT
Communications Conference, 1998.
- Cardillo, P. and Clements, M. High Speed Wordspotting for Archive Retrieval, Georgia
Tech Wireless Symposium, 1999.
- Cardillo, P. and Clements, M. High Speed Forward-Backward
Wordspotting, Georgia
Center for Advanced Communications Technologies, NIGHTLIGHT, Jan 18, 2000.
- Jon Arrowood, Brian Delaney, Mark Clements, Nikil Jayant,
Voice User Interfaces
for Wireless PDAs, YAMACRAW Conference, October 18, 2000.
- Mark Clements, The Yamacraw User Interface, YAMACRAW
Conference, October 19, 2000.
Technical/Research Reports
- M. A. Clements, ``An Investigation of Perceptual Distance
Measures for Speech,'' Final Report, RADC Contract F30602-81-C-0185, Feb. 1984.
- T. P. Barnwell and M. A. Clements, ``Improved Compactly
Computable Objective Measures for Predicting the Acceptability of Speech
Communications Systems,'' Final Report, DCA Contract DCA-100-83-C-0027,
June 1984.
- M. A. Clements, ``Adaptation and Development of Speech
Recognition Techniques as Applied to Improving Communications for
Individuals with Hearing Impairments,'' Final Report, NSF Contract
ECS-8206409, July 1985.
- J. H. Hansen and M. A. Clements, ``Speech Enhancement for
Automatic Recognition,'' Final Report, Lockheed Contract 1084637,
Sept. 1985.
- R. Cole, Lynette Hirschman, et al. (including
Mark Clements), ``Workshop of Spoken Language
Understanding," Oregon Graduate Institute Technical Report No. C/SE 92-014,
September 1, 1992. (This was a 63 page report of an NSF-sponsored
two-day invited workshop to determine future trends and needs of automatic
speech recognition research.)
- Lim, Su How and Clements, Identification of Cancerous Tissue via Raman Spectroscopy,
Report to Visionex, Inc., 1999.
May 2002