DSpace at KISTKIST Article2007

Full metadata record

DC Field Value Language
dc.contributor.authorKwon, Soonil-
dc.contributor.authorNarayanan, Shrikanth-
dc.date.accessioned2024-01-21T01:35:03Z-
dc.date.available2024-01-21T01:35:03Z-
dc.date.created2021-08-31-
dc.date.issued2007-01-01-
dc.identifier.issn0167-8655-
dc.identifier.urihttps://pubs.kist.re.kr/handle/201004/134752-
dc.description.abstractA new method for speaker identification that selectively uses feature vectors for robust decision-making is described. Experimental results, with short speech segments ranging from 0.25 to 2 s, showed that our method consistently outperforms other approaches yielding relative improvements of 20-51% and 15-30% over baseline GMM and the LDA-GMM systems, respectively. (c) 2006 Elsevier B.V. All rights reserved.-
dc.languageEnglish-
dc.publisherELSEVIER-
dc.titleRobust speaker identification based on selective use of feature vectors-
dc.typeArticle-
dc.identifier.doi10.1016/j.patrec.2006.06.009-
dc.description.journalClass1-
dc.identifier.bibliographicCitationPATTERN RECOGNITION LETTERS, v.28, no.1, pp.85 - 89-
dc.citation.titlePATTERN RECOGNITION LETTERS-
dc.citation.volume28-
dc.citation.number1-
dc.citation.startPage85-
dc.citation.endPage89-
dc.description.journalRegisteredClassscie-
dc.description.journalRegisteredClassscopus-
dc.identifier.wosid000242552900010-
dc.identifier.scopusid2-s2.0-33750470047-
dc.relation.journalWebOfScienceCategoryComputer Science, Artificial Intelligence-
dc.relation.journalResearchAreaComputer Science-
dc.type.docTypeArticle-
dc.subject.keywordAuthorshort-segment speaker identification-
dc.subject.keywordAuthorspeaker model construction-
dc.subject.keywordAuthorfeature vector selection-
dc.subject.keywordAuthorlinear discriminant analysis (LDA)-
Appears in Collections:
KIST Article > 2007
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML
Show Simple Item Record

qrcode

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

BROWSE