Photo file: 
Full name: 
Mark A Clements
Job title: 
Professor
; Director, Interactive Media Technology Center; Joseph M. Pettit Professor in Digital Signal Processing
Technical Interest Groups: Bioengineering, Digital Signal Processing
Email address: 
Work phone: 
404/894-4584
Fax: 
404.894.8363
Office: 
Cent 5226

Dr. Mark A. Clements received the S.B. degree in 1976, the S.M. degree in 1978, the electrical engineering degree in 1979 and the Sc.D. degree in 1982, all in electrical engineering and computer science from Massachusetts Institute of Technology.

During his graduate work, he received a National Institutes of Health fellowship. His Sc.D. thesis was concerned with sensory aids for the hearing impaired. While pursuing his Sc.D., he also worked in the development of real-time automatic speech recognition systems.

Dr. Clements is a member of the Acoustical Society of America and is a Fellow of the IEEE. He has been a member of the IEEE Speech Technical Committee, and has served as an Editor for IEEE Transactions on Acoustics, Speech, and Signal Processing. He also has been on the Board of Governors for the IEEE Signal Processing Society. He currently serves as Director of Georgia Tech's Interactive Media Technology Center.

Research interests: 
  • 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
Distinctions: 
  • Supervised Investors Award for Teaching 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
  • Fellow IEEE
  • IEEE Speech Technical Committee, 1987-1991
  • IEEE Acoustics, Speech and Signal Processing, Associate Editor, 1989-1991
  • Technical Program Chairman, ICASSP-96
  • Board of Governors, IEEE Signal Processing Society 2003-2007

Elliot Moore, Mark Clements, John Peifer, and Lydia Weisser, "Investigating the Impact of Voice Source Analysis in Classifying Clinical Depression," IEEE Transactions on Biomedical Engineering, vol. 55, no. 1, pp. 96-108, January 2008.

Mark Clements and Marsal Gavaldà, "Voice/Audio Information Retrieval: Minimizing the Need for Human Ears," In Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Kyoto, December 2007 (invited paper and talk).

"Phonetic Searching," Peter Cardillo, Mark Clements, Ed Price, Patent Number, 7,263,484, Granted August 28, 2007.

Kaustubh Kalgaonkar and Mark Clements, "Vocal Tract and Area Function Estimation with both Lip and Glottal Losses," Proceedings of InterSpeech, Antwerp, August 2007.

Matthew E. Lee, Adriane Swalm Durey, Elliot Moore, and Mark Clements, "Ultra Low Bit Rate Speech Coding Using an Ergodic Hidden Markov Model," International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Philadelphia, March 2005.

Robert Morris and Mark Clements, "Reconstruction of Speech from Whispers," International Journal of Medical Engineering and Physics, Dec 2002, pp 515-520.

Xiaozheng Zhang, Charles C. Broun, Russell M. Mersereau, Mark A. Clements, "Automatic Speechreading with Applications to Human-Computer Interfaces," EURASIP JASP special Issue on Joint Audio-Visual Speech Processing, October 2002, pp1228-1248.

G. Miao and M. Clements, Digital Signal Processing and Statistical Pattern Recognition, Artech House, 508 pages, June 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.

"Singing Voice Synthesis," with E. George, M. Macon, L. Jensen-Link, J. Oliverio, Patent number 6,304,846, Granted: October 16, 2001.

"Apparatus and Method for Modifying a Speech Waveform to Compensate for Recruitment of Loudness," Patent number 5,274,711, Granted: December 27, 1993.

S. R. Quackenbush, T. P. Barnwell, and M. A. Clements, Objective Measures for Speech Quality Testing, Prentice-Hall, Englewood Cliffs, NJ 1988.

Last revised May 3, 2016