한국어 연속 숫자음 기반의 화자인식
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 반제미 | - |
dc.contributor.author | 권영헌 | - |
dc.date.accessioned | 2021-06-23T15:07:01Z | - |
dc.date.available | 2021-06-23T15:07:01Z | - |
dc.date.issued | 2009-07 | - |
dc.identifier.issn | 2005-9051 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/41049 | - |
dc.description.abstract | 한국어 연속 숫자음을 DB로 사용하는 화자인식기를 구성하여 그 성능을 살펴보았다. 특 징벡터는 각각의 음성에서 구한 39차의 MFCC를 이용하였고 인식기는 CHMM을 이용하였다. 훈 련숫자에 따른 인식률 변화를 알아보았고 또한 mixture 증가에 따른 인식률 변화를 알아보았다. | - |
dc.description.abstract | We studied speaker recognition system using Korean connected digits. After extracting 39 order feature coefficient of MFCC from DB of Korean connected digits, we perform We investigated the change of speech recognition rate training and recognition using CHMM. according to numbers of mixture. | - |
dc.format.extent | 6 | - |
dc.language | 한국어 | - |
dc.language.iso | KOR | - |
dc.publisher | 한양대학교 이학기술연구소 | - |
dc.title | 한국어 연속 숫자음 기반의 화자인식 | - |
dc.title.alternative | Speaker Recognition using Korean Connected Digits | - |
dc.type | Article | - |
dc.publisher.location | 대한민국 | - |
dc.identifier.bibliographicCitation | 이학기술연구지, v.13, pp 19 - 24 | - |
dc.citation.title | 이학기술연구지 | - |
dc.citation.volume | 13 | - |
dc.citation.startPage | 19 | - |
dc.citation.endPage | 24 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | domestic | - |
dc.subject.keywordAuthor | Speaker Recognition | - |
dc.subject.keywordAuthor | Korean connected digits | - |
dc.identifier.url | http://www.earticle.net/Article.aspx?sn=110470 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
55 Hanyangdeahak-ro, Sangnok-gu, Ansan, Gyeonggi-do, 15588, Korea+82-31-400-4269 sweetbrain@hanyang.ac.kr
COPYRIGHT © 2021 HANYANG UNIVERSITY. ALL RIGHTS RESERVED.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.