Real-time statistical time-series analyzer for speech segmentation

dc.contributor.advisorHayre, Harbhajan S.
dc.contributor.committeeMemberSchneider, William P.
dc.contributor.committeeMemberMotard, Rodolphe L.
dc.creatorStewart, Carrington H.
dc.description.abstractThis thesis presents results of a research effort designed to advance the development of an acoustic speech segmentation procedure reported by an earlier researcher. The procedure is known as 'moment analysis of the reciprocal zero crossing distances of speech.' The development of this procedure is advanced through the design and construction of a real-time statistical time-series analyzer to eliminate the need for computer analysis. This work discusses the general needs to which the advancement of the development of this segmentation procedure can be useful. Then it is shown that an electronic real-time statistical time-series analyzer is an effective method to advance the development of the segmentation procedure. In addition, a discussion of the design concepts and design feasibility is presented. Finally, the paper shows that the design concept is feasible and that the analyzer design is physically realizable, thus illustrating that the need for computer analysis to study and utilize the most promising aspect of the segmentation procedure is essentially eliminated.
dc.description.departmentElectrical and Computer Engineering, Department of
dc.format.digitalOriginreformatted digital
dc.rightsThis item is protected by copyright but is made available here under a claim of fair use (17 U.S.C. Section 107) for non-profit research and educational purposes. Users of this work assume the responsibility for determining copyright status prior to reusing, publishing, or reproducing this item for purposes other than what is allowed by fair use or other copyright exemptions. Any reuse of this item in excess of fair use or other copyright exemptions requires express permission of the copyright holder.
dc.titleReal-time statistical time-series analyzer for speech segmentation
dc.type.genreThesis of Engineering Engineering, Department of Engineering of Houston of Science


Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
3.87 MB
Adobe Portable Document Format