Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 이건상 | - |
dc.date.accessioned | 2020-09-14T00:20:27Z | - |
dc.date.available | 2020-09-14T00:20:27Z | - |
dc.date.issued | 2004-12 | - |
dc.identifier.citation | 이학기술연구지, v.7, Page.53-58 | en_US |
dc.identifier.uri | https://www.earticle.net/Article/A106192 | - |
dc.identifier.uri | https://repository.hanyang.ac.kr/handle/20.500.11754/153800 | - |
dc.description.abstract | This paper studies the performances of MAP(Maximum a Posterior re-estimation), MLLR(Maximal Likelihood Linear Regression) and the combined method of each basic schemes. RCT(Regression Class Tree) is extended to MLLR. Database of korean 4 continuous digit numbers is used. Trained data are 4410 of man's voice and 3610 woman's one. We use test data of 980 of man's voice and 910 of woman's one. As a result, we obtain better recognition rate for system that combines each basic schemes than one that has a basic scheme. Also we get better recognition rate as class node, mixture number and the suitable tree depth increase. | en_US |
dc.language.iso | ko_KR | en_US |
dc.publisher | 한양대학교 이학기술연구소 | en_US |
dc.title | 화자적응을 위한 알고리즘 개선 | en_US |
dc.title.alternative | Improvement of Speaker Adaptation Algorithm | en_US |
dc.type | Article | en_US |
dc.relation.journal | 이학기술연구지 | - |
dc.contributor.googleauthor | 함동훈 | - |
dc.contributor.googleauthor | 박정재 | - |
dc.contributor.googleauthor | 권영현 | - |
dc.contributor.googleauthor | 이건상 | - |
dc.relation.code | 2012101941 | - |
dc.sector.campus | E | - |
dc.sector.daehak | COLLEGE OF SCIENCE & TECHNOLOGY[E] | - |
dc.sector.department | DIVISION OF SCIENCE & TECHNOLOGY | - |
dc.identifier.pid | albertlee | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.