Show simple item record

dc.contributor.advisorPanahi, Issa M. S.
dc.creatorBhat, Gautam Shreedhar
dc.date.accessioned2018-08-06T14:52:10Z
dc.date.available2018-08-06T14:52:10Z
dc.date.created2018-05
dc.date.issued2018-05
dc.date.submittedMay 2018
dc.identifier.urihttp://hdl.handle.net/10735.1/5926
dc.description.abstractSpeech Enhancement (SE) is elemental in many real world applications. In the last two decades, extensive studies have been carried out on single and multi-channel SE techniques. In this thesis, three novel SE algorithms have been proposed that can be used for Hearing Aid Devices using a smartphone as their assistive device. The first SE method exploits the information of formant locations to improve the speech quality and intelligibility of the Super-Gaussian Joint Maximum aposterori (SGJMAP) SE method. The second method is the extension of this work on the Log Spectral Minimum Mean Square Error Amplitude Estimator (Log-MMSE) which is a well-known SE algorithm. The third method is a real time Blind Source Separation (BSS) method based on Independent Vector Analysis (IVA) for convolutive mixtures. Objective and subjective evaluation of the developed techniques show substantial improvements in speech quality and intelligibility.
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.rights©2018 The Author. Digital access to this material is made possible by the Eugene McDermott Library. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.
dc.subjectSpeech, Intelligibility of
dc.subjectSpeech perception
dc.subjectHearing aids—Design and construction
dc.subjectSmartphones
dc.subjectReal-time control
dc.subjectAssistive listening systems
dc.subjectFormants (Speech)
dc.titleSmartphone-Based Single and Dual Microphone Speech Enhancement Algorithms for Hearing Study
dc.typeThesis
dc.date.updated2018-08-06T14:52:11Z
dc.type.materialtext
dc.contributor.ORCID0000-0002-5510-6385 (Bhat, GS)
thesis.degree.grantorThe University of Texas at Dallas
thesis.degree.departmentElectrical Engineering
thesis.degree.levelMasters
thesis.degree.nameMSEE


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record