Isolated Words Recognition using K-means iteration without Initialization

초기화하지 않은 K-means iteration을 이용한 고립단어 인식

  • 김진영 (서울대학교 전자공학과) ;
  • 성굉모 (서울대학교 전자공학과)
  • Published : 1988.07.01

Abstract

K-means iteration method is generally used for creating the templates in speaker-independent isolated-word recognition system. In this paper the initialization method of initial centers is proposed. The concepts are sorting and trace segmentation. All the tokens are sorted and segmented by trace segmentation so that initial centers are decided. The performance of this method is evaluated by isolated-word recognition of Korean digits. The highest recognition rate is 97.6%.

Keywords