Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 장준혁 | - |
dc.date.accessioned | 2018-03-09T05:41:36Z | - |
dc.date.available | 2018-03-09T05:41:36Z | - |
dc.date.issued | 2013-07 | - |
dc.identifier.citation | JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA 권: 134 호: 1 페이지: EL70-EL76 | en_US |
dc.identifier.issn | 0001-4966 | - |
dc.identifier.uri | http://dx.doi.org/10.1121/1.4809770 | - |
dc.identifier.uri | http://hdl.handle.net/20.500.11754/44209 | - |
dc.description | MEST | en_US |
dc.description.abstract | This paper proposes a voice activity detection (VAD) method in a kernel subspace domain to improve the performance of the kernel-based VAD. A linear transform matrix that can simultaneously diagonalize the two covariance matrices using kernel principal component analysis is presented to generate the kernel subspace. The likelihood ratio test based on Gaussian distributions is applied for the VAD in the kernel subspace. Experimental results show that the proposed VAD algorithm outperforms the conventional approaches under various noise conditions. (C) 2013 Acoustical Society of America | en_US |
dc.description.sponsorship | NRF | en_US |
dc.language.iso | en | en_US |
dc.publisher | ACOUSTICAL SOC AMER AMER INST PHYSICS, STE 1 NO 1, 2 HUNTINGTON QUADRANGLE, MELVILLE, NY 11747-4502 USA | en_US |
dc.subject | MODEL | en_US |
dc.title | Enhanced voice activity detection in kernel subspace domain | en_US |
dc.type | Article | en_US |
dc.relation.volume | 134 | - |
dc.identifier.doi | 10.1121/1.4809770 | - |
dc.relation.page | 70-76 | - |
dc.relation.journal | JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA | - |
dc.contributor.googleauthor | Kim, Dong Kook | - |
dc.contributor.googleauthor | Shin, Jong Won | - |
dc.contributor.googleauthor | Chang, Joon-Hyuk | - |
dc.relation.code | 2013011011 | - |
dc.sector.campus | S | - |
dc.sector.daehak | COLLEGE OF ENGINEERING[S] | - |
dc.sector.department | DEPARTMENT OF ELECTRONIC ENGINEERING | - |
dc.identifier.pid | jchang | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.