Please use this identifier to cite or link to this item: https://hdl.handle.net/11147/4792
Full metadata record
DC FieldValueLanguage
dc.contributor.authorDrugman, Thomas-
dc.contributor.authorBozkurt, Barış-
dc.contributor.authorDutoit, Thierry-
dc.date.accessioned2017-02-06T09:13:40Z-
dc.date.available2017-02-06T09:13:40Z-
dc.date.issued2012-01-
dc.identifier.citationDrugman, T., Bozkurt, B., and Dutoit, T. (2012). A comparative study of glottal source estimation techniques. Computer Speech and Language, 26(1), 20-34. doi:10.1016/j.csl.2011.03.003en_US
dc.identifier.issn0885-2308-
dc.identifier.urihttp://doi.org/10.1016/j.csl.2011.03.003-
dc.identifier.urihttp://hdl.handle.net/11147/4792-
dc.description.abstractAbstract: Source-tract decomposition (or glottal flow estimation) is one of the basic problems of speech processing. For this, several techniques have been proposed in the literature. However, studies comparing different approaches are almost nonexistent. Besides, experiments have been systematically performed either on synthetic speech or on sustained vowels. In this study we compare three of the main representative state-of-the-art methods of glottal flow estimation: closed-phase inverse filtering, iterative and adaptive inverse filtering, and mixed-phase decomposition. These techniques are first submitted to an objective assessment test on synthetic speech signals. Their sensitivity to various factors affecting the estimation quality, as well as their robustness to noise are studied. In a second experiment, their ability to label voice quality (tensed, modal, soft) is studied on a large corpus of real connected speech. It is shown that changes of voice quality are reflected by significant modifications in glottal feature distributions. Techniques based on the mixed-phase decomposition and on a closed-phase inverse filtering process turn out to give the best results on both clean synthetic and real speech signals. On the other hand, iterative and adaptive inverse filtering is recommended in noisy environments for its high robustness. © 2011 Elsevier Ltd. All rights reserved.en_US
dc.description.sponsorshipBelgian Fonds National de la Recherche Scientifique (FNRS)en_US
dc.language.isoenen_US
dc.publisherElsevier Ltd.en_US
dc.relation.ispartofComputer Speech and Languageen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectGlottal flow estimationen_US
dc.subjectInverse filteringen_US
dc.subjectMixed-phase decompositionen_US
dc.subjectVoice qualityen_US
dc.subjectSource-tract separationen_US
dc.titleA comparative study of glottal source estimation techniquesen_US
dc.typeArticleen_US
dc.authoridTR115225en_US
dc.departmentIzmir Institute of Technology. Electronics and Communication Engineeringen_US
dc.identifier.volume26en_US
dc.identifier.issue1en_US
dc.identifier.startpage20en_US
dc.identifier.endpage34en_US
dc.identifier.wosWOS:000295810600002
dc.identifier.scopusSCOPUS:2-s2.0-80955173659
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.identifier.doi10.1016/j.csl.2011.03.003-
dc.relation.doi10.1016/j.csl.2011.03.003en_US
dc.coverage.doi10.1016/j.csl.2011.03.003en_US
item.openairetypeArticle-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.languageiso639-1en-
item.fulltextWith Fulltext-
item.cerifentitytypePublications-
item.grantfulltextopen-
Appears in Collections:Electrical - Electronic Engineering / Elektrik - Elektronik Mühendisliği
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Sürdürülebilir Yeşil Kampüs Koleksiyonu / Sustainable Green Campus Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection
Files in This Item:
File Description SizeFormat 
4792.pdfMakale1.29 MBAdobe PDFThumbnail
View/Open
Show simple item record

CORE Recommender

SCOPUSTM   
Citations

79
checked on Oct 23, 2021

WEB OF SCIENCETM
Citations

70
checked on Oct 23, 2021

Page view(s)

18
checked on Oct 28, 2021

Download(s)

28
checked on Oct 28, 2021

Google ScholarTM

Check

Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.