DC Field | Value | Language |
---|---|---|
dc.contributor.author | 이지연 | ko |
dc.contributor.author | 정상배 | ko |
dc.contributor.author | 최홍식 | ko |
dc.contributor.author | 한민수 | ko |
dc.date.accessioned | 2009-12-21T04:51:48Z | - |
dc.date.available | 2009-12-21T04:51:48Z | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.issued | 2008-06 | - |
dc.identifier.citation | 말소리, v.1, no.66, pp.61 - 72 | - |
dc.identifier.issn | 1226-1173 | - |
dc.identifier.uri | http://hdl.handle.net/10203/15399 | - |
dc.description.abstract | This paper proposes a method to improve pathological and normal voice classification performance by combining multiple features such as auditory-based and higher-order features. Their performances are measured by Gaussian mixture models (GMMs) and linear discriminant analysis (LDA). The combination of multiple features proposed by the frame-based LDA method is shown to be an effective method for pathological and normal voice classification, with a 87.0% classification rate. This is a noticeable improvement of 17.72% compared to the MFCC-based GMM algorithm in terms of error reduction. | - |
dc.language | Korean | - |
dc.language.iso | ko | en |
dc.publisher | 대한음성학회 | - |
dc.title | HOS 특징 벡터를 이용한 장애 음성 분류 성능의 향상 | - |
dc.title.alternative | Performance Improvement of Classification Between Pathological and Normal Voice Using HOS Parameter | - |
dc.type | Article | - |
dc.type.rims | ART | - |
dc.citation.volume | 1 | - |
dc.citation.issue | 66 | - |
dc.citation.beginningpage | 61 | - |
dc.citation.endingpage | 72 | - |
dc.citation.publicationname | 말소리 | - |
dc.embargo.liftdate | 9999-12-31 | - |
dc.embargo.terms | 9999-12-31 | - |
dc.identifier.kciid | ART001263793 | - |
dc.contributor.localauthor | 한민수 | - |
dc.contributor.nonIdAuthor | 이지연 | - |
dc.contributor.nonIdAuthor | 정상배 | - |
dc.contributor.nonIdAuthor | 최홍식 | - |
dc.subject.keywordAuthor | Pathological voice detection | - |
dc.subject.keywordAuthor | Gaussian mixture model | - |
dc.subject.keywordAuthor | Linear discriminant analysis | - |
dc.subject.keywordAuthor | Classification and regression tree. | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.