Summarizing popular music via structural similarity analysis

被引：36

作者：

Cooper, M ^{[1
]}

Foote, J ^{[1
]}

机构：

[1] FX Palo Alto Lab, Palo Alto, CA 94304 USA

来源：

2003 IEEE WORKSHOP ON APPLICATIONS OF SIGNAL PROCESSING TO AUDIO AND ACOUSTICS PROCEEDINGS | 2003年

关键词：

D O I：

10.1109/ASPAA.2003.1285836

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

We present a framework for summarizing digital media based on structural analysis. Though these methods are applicable to general media, we concentrate here on characterizing repetitive structure in popular music. In the first step, a similarity matrix is calculated from inter-frame spectral similarity. Segment boundaries, such as verse-chorus transitions, are found by correlating a kernel along the diagonal of the matrix. Once segmented, spectral statistics of each segment are computed. In the second step, segments are clustered based on the pairwise similarity of their statistics, using a matrix decomposition. Finally, the audio is summarized by combining segments representing the clusters most frequently repeated throughout the piece. We present results on a small corpus showing more than 90% correct detection of verse and chorus segments.

引用

页码：127 / 130

页数：4

共 14 条

[1]

Bartsch M. A., 2001, P IEEE WASPAA

[2]

CHU S, 2000, P IEEE INT C AC SPEE

[3]

Church K.W., 1993, J COMPUT GRAPH STAT, V2, P153, DOI [10.2307/1390697, DOI 10.2307/1390697, DOI 10.1080/10618600.1993.10474605, 10.1080/10618600.1993, DOI 10.1080/10618600.1993]

[4]

COOPER M, 2002, P 3 INT C MUS INF RE, P81

[5]

Cover T. M., 2005, ELEM INF THEORY, DOI 10.1002/047174882X

[6] Robust real-time periodic motion detection, analysis, and applications [J].

Cutler, R ;

Davis, LS .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2000, 22 (08) :781-796

[7] RECURRENCE PLOTS OF DYNAMIC-SYSTEMS [J].

ECKMANN, JP ;

KAMPHORST, SO ;

RUELLE, D .

EUROPHYSICS LETTERS, 1987, 4 (09) :973-977

[8]

Foote J, 2000, 2000 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, PROCEEDINGS VOLS I-III, P452, DOI 10.1109/ICME.2000.869637

[9] Media segmentation using self-similarity decomposition [J].

Foote, JT ;

Cooper, ML .

STORAGE AND RETRIEVAL FOR MEDIA DATABASES 2003, 2003, 5021 :167-175

[10]

GONG Y, 2000, P IEEE INT C COMP VI

← 1 2 →