To catch a chorus: Using chroma-based representations for audio thumbnailing

被引：81

作者：

Bartsch, MA ^{[1
]}

Wakefield, GH ^{[1
]}

机构：

[1] Univ Michigan, Dept EECS, Ann Arbor, MI 48109 USA

来源：

PROCEEDINGS OF THE 2001 IEEE WORKSHOP ON THE APPLICATIONS OF SIGNAL PROCESSING TO AUDIO AND ACOUSTICS | 2001年

关键词：

D O I：

10.1109/ASPAA.2001.969531

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

An important application for use with multimedia databases is a browsing aid, which allows a user to quickly and efficiently preview selections from either a database or from the results of a database query. Methods for facilitating browsing, though, are necessarily media dependent. We present one such method that produces short, representative samples (or "audio thumbnails") of selections of popular music. This method attempts to identify the chorus or refrain of a song by identifying repeated sections of the audio waveform. A reduced spectral representation of the selection based on a chroma transformation of the spectrum is used to find repeating patterns. This representation encodes harmonic relationships in a signal and thus is ideal for popular music, which is often characterized by prominent harmonic progressions. The method is evaluated over a sizable database of popular music and found to perform well, with most of the errors resulting from songs that do not meet our structural assumptions.

引用

页码：15 / 18

页数：4

共 8 条

[1]

[Anonymous], 1986, PSYCHOL MUSIC, DOI [10.1177/0305735686141004, DOI 10.1177/0305735686141004]

[2]

Dixon S., 2000, P AAAI WORKSH ART IN

[3] Visualizing music and audio using self-similarity [J].

Foote, J .

ACM MULTIMEDIA 99, PROCEEDINGS, 1999, :77-80

[4]

FOOTE J, 2000, P IEEE INT C MULT EX, V1, P452

[5]

LOGAN B, 2000, INT C AC SPEECH SIGN

[6]

Rabiner L., 1993, Fundamentals of Speech Recognition

[7] CIRCULARITY IN JUDGMENTS OF RELATIVE PITCH [J].

SHEPARD, RN .

JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1964, 36 (12) :2346-+

[8]

WAKEFIELD GH, 1999, SPIE DENV COL

← 1 →