Improvement of MP3-Based Music Summarization Using Linear Regression

선형 근사를 통한 MP3 음악 요약의 성능 향상

  • Koh, Seo-Young (Department of Computer Science Korea Advanced Institute of Science and Technology) ;
  • Park, Jeong-Sik (Department of Computer Science Korea Advanced Institute of Science and Technology) ;
  • Oh, Yung-hwan (Department of Computer Science Korea Advanced Institute of Science and Technology)
  • 고서영 (한국과학기술원 전자전산학과 전산학) ;
  • 박정식 (한국과학기술원 전자전산학과 전산학) ;
  • 오영환 (한국과학기술원 전자전산학과 전산학)
  • Published : 2005.11.17

Abstract

Music Summarization is to extract there presentative section of a song such as chorus or motif. In previous work, the length of music summarization was fixed, and the threshold to determine the chorus section was so sensitive that the tuning was needed. Also, the rapid change of rhythm or variation of sound effects make the chorus extraction errors. We suggest the linear regression for extracting the changeable length and for minimizing the effects of threshold variation. The experimental result shows that proposed method outperforms conventional one.

Keywords