Investigating Speaker Features From Very Short Speech Records

dc.contributor.authorBerg, Brian LaRoyen
dc.contributor.committeechairBeex, A. A. Louisen
dc.contributor.committeememberReed, Jeffrey H.en
dc.contributor.committeememberJacobs, Iraen
dc.contributor.committeememberVanLandingham, Hugh F.en
dc.contributor.committeememberBall, Joseph A.en
dc.contributor.departmentElectrical and Computer Engineeringen
dc.date.accessioned2014-03-14T20:15:20Zen
dc.date.adate2001-09-11en
dc.date.available2014-03-14T20:15:20Zen
dc.date.issued2001-07-23en
dc.date.rdate2002-09-11en
dc.date.sdate2001-08-17en
dc.description.abstractA procedure is presented that is capable of extracting various speaker features, and is of particular value for analyzing records containing single words and shorter segments of speech. By taking advantage of the fast convergence properties of adaptive filtering, the approach is capable of modeling the nonstationarities due to both the vocal tract and vocal cord dynamics. Specifically, the procedure extracts the vocal tract estimate from within the closed glottis interval and uses it to obtain a time-domain glottal signal. This procedure is quite simple, requires minimal manual intervention (in cases of inadequate pitch detection), and is particularly unique because it derives both the vocal tract and glottal signal estimates directly from the time-varying filter coefficients rather than from the prediction error signal. Using this procedure, several glottal signals are derived from human and synthesized speech and are analyzed to demonstrate the glottal waveform modeling performance and kind of glottal characteristics obtained therewith. Finally, the procedure is evaluated using automatic speaker identity verification.en
dc.description.degreePh. D.en
dc.identifier.otheretd-08172001-164442en
dc.identifier.sourceurlhttp://scholar.lib.vt.edu/theses/available/etd-08172001-164442/en
dc.identifier.urihttp://hdl.handle.net/10919/28691en
dc.publisherVirginia Techen
dc.relation.haspartafrif_berg.pdfen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectSpeaker Recognitionen
dc.subjectSpeech Synthesisen
dc.subjectSpeech Analysisen
dc.subjectDigital Signal Processingen
dc.subjectSpeaker Identity Verificationen
dc.subjectSpeech Processingen
dc.titleInvestigating Speaker Features From Very Short Speech Recordsen
dc.typeDissertationen
thesis.degree.disciplineElectrical and Computer Engineeringen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.leveldoctoralen
thesis.degree.namePh. D.en

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
afrif_berg.pdf
Size:
9.84 MB
Format:
Adobe Portable Document Format