Proceedings of the KSPS conference (대한음성학회:학술대회논문집)
- 2007.05a
- /
- Pages.45-48
- /
- 2007
Flexible selection of feature vectors for speaker identification
화자 인식을 위한 특징 벡터의 유연한 선택
- Yoon, Sang-Min (Korea Advanced Institute of Science and Technology) ;
- Park, Gyeong-Mi (Korea Advanced Institute of Science and Technology) ;
- Kim, Gil-Yeon (Korea Advanced Institute of Science and Technology) ;
-
O, Yeong-Hwan
(Korea Advanced Institute of Science and Technology)
- 윤상민 (한국과학기술원 전자전산학과 전산학) ;
- 박경미 (한국과학기술원 전자전산학과 전산학) ;
- 김길연 (한국과학기술원 전자전산학과 전산학) ;
-
오영환
(한국과학기술원 전자전산학과 전산학)
- Published : 2007.05.18
Abstract
This paper proposes a flexible selection method of feature vectors for speaker identification. In speaker identification, overlapped region between speaker models lowers the accuracy. Recently, a method was proposed which discards overlapped feature vectors without regard to the source causing the overlap. We suggest a new method using both overlapped features among speakers and non-overlapped features to mitigate the overlap effects.
Keywords