Retargeting Expressive Musical Style from Classical Music Recordings Using a Support Vector Machine

被引：0
作者：
Lui, Simon [1 ]
Horner, Andrew [1 ,2 ]
So, Clifford [3 ]
机构：
[1] Hong Kong Univ Sci & Technol, Dept Comp Sci & Engn, Hong Kong, Hong Kong, Peoples R China
[2] Hong Kong Univ Sci & Technol, Dept Comp Sci, Hong Kong, Hong Kong, Peoples R China
[3] Chinese Univ Hong Kong, Sch Continuing & Profess Studies, Hong Kong, Hong Kong, Peoples R China
来源：
JOURNAL OF THE AUDIO ENGINEERING SOCIETY | 2010年 / 58卷 / 12期
关键词：
PERFORMANCES;
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
A method for retargeting musical style from audio recordings to MIDI is proposed. First the audio file is divided into phrases according to cadence, pitch pattern, and local energy. The phrases are then trained with SVM to obtain the style parameters, including dynamics, tempo, and articulation. The extracted performance style is then applied to a raw MIDI note list to make it expressive. Experiments show that this method reproduces a performer's style with a high level of correlation to real performances.
引用
收藏
页码：1032 / 1044
页数：13
相关论文
共 26 条
  • [1] [Anonymous], 2002, P INT COMPUTER MUSIC
  • [2] [Anonymous], 1990, COGNITIVE FDN MUSICA
  • [3] [Anonymous], COMPL MIDI 1 0 DET S
  • [4] ASSAYAG G, 1999, P ICMC 99 BEIJ CHIN
  • [5] Chai W., 2001, P INT C ART INT
  • [6] DANNENBERG RB, 2002, INT C MUS INF RETR
  • [7] Automatic extraction of tempo and beat from expressive performances
    Dixon, S
    [J]. JOURNAL OF NEW MUSIC RESEARCH, 2001, 30 (01) : 39 - 58
  • [8] DONGARRA JJ, 1990, ACM T MATH SOFTWARE, V16, P1, DOI 10.1145/77626.79170
  • [9] Generating musical performances with Director Musices
    Friberg, A
    Colombo, V
    Frydén, L
    Sundberg, J
    [J]. COMPUTER MUSIC JOURNAL, 2000, 24 (03) : 23 - 29
  • [10] Friberg A., 1995, QUANTITATIVE RULE SY
123