Enhanced voice activity detection in kernel subspace domain
- Authors
- Kim, Dong Kook; Shin, Jong Won; Chang, Joon-Hyuk
- Issue Date
- Jul-2013
- Publisher
- ACOUSTICAL SOC AMER AMER INST PHYSICS
- Citation
- JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, v.134, no.1, pp.EL70 - EL76
- Indexed
- SCIE
SCOPUS
- Journal Title
- JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA
- Volume
- 134
- Number
- 1
- Start Page
- EL70
- End Page
- EL76
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/26684
- DOI
- 10.1121/1.4809770
- ISSN
- 0001-4966
- 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
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - 서울 공과대학 > 서울 융합전자공학부 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/26684)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.