M
Mark A. Clements
Researcher at Georgia Institute of Technology
Publications - 155
Citations - 3821
Mark A. Clements is an academic researcher from Georgia Institute of Technology. The author has contributed to research in topics: Speech processing & Hidden Markov model. The author has an hindex of 33, co-authored 155 publications receiving 3637 citations. Previous affiliations of Mark A. Clements include University of Cambridge & Duke University.
Papers
More filters
Journal ArticleDOI
Constrained iterative speech enhancement with application to speech recognition
TL;DR: The algorithms are evaluated with respect to improving automatic recognition of speech in the presence of additive noise and shown to outperform other enhancement methods in this application.
Journal ArticleDOI
Critical Analysis of the Impact of Glottal Features in the Classification of Clinical Depression in Speech
TL;DR: Analysis of discriminating feature sets used in the study reflect a clear indication that glottal descriptors are vital components of vocal affect analysis.
Patent
Singing voice synthesis
TL;DR: In this article, a method of singing voice synthesis using commercially available MIDI-based music composition software as a user interface is presented. But it is not suitable for the use of speech recognition.
Journal ArticleDOI
The challenge of spoken language systems: Research directions for the nineties
R. Cole,Lynette Hirschman,Les Atlas,Mary E. Beckman,Alan W. Biermann,M. Bush,Mark A. Clements,L. Cohen,Oscar N. Garcia,Brian A. Hanson,Hynek Hermansky,Stephen E. Levinson,Kathleen R. McKeown,Nelson Morgan,David G. Novick,Mari Ostendorf,Sharon Oviatt,Patti Price,Harvey F. Silverman,J. Spiitz,Alex Waibel,Cliff Weinstein,Stephen A. Zahorian,Victor W. Zue +23 more
TL;DR: The need for multidisciplinary research is reviewed, for development of shared corpora and related resources, for computational support and far rapid communication among researchers, and the expected benefits of this technology are reviewed.
Proceedings ArticleDOI
Decoding Children's Social Behavior
James M. Rehg,Gregory D. Abowd,Agata Rozga,Mario Romero,Mark A. Clements,Stan Sclaroff,Irfan Essa,Opal Y. Ousley,Yin Li,Chanho Kim,Hrishikesh Rao,Jonathan C. Kim,Liliana Lo Presti,Jianming Zhang,Denis Lantsman,Jonathan Bidwell,Zhefan Ye +16 more
TL;DR: A new publicly-available dataset containing over 160 sessions of a 3-5 minute child-adult interaction designed to elicit a broad range of social behaviors based on video and audio data is introduced.