Translator Disclaimer
24 October 2005 Musical structure analysis using similarity matrix and dynamic programming
Author Affiliations +
Proceedings Volume 6015, Multimedia Systems and Applications VIII; 601516 (2005) https://doi.org/10.1117/12.633792
Event: Optics East 2005, 2005, Boston, MA, United States
Abstract
Automatic music segmentation and structure analysis from audio waveforms based on a three-level hierarchy is examined in this research, where the three-level hierarchy includes notes, measures and parts. The pitch class profile (PCP) feature is first extracted at the note level. Then, a similarity matrix is constructed at the measure level, where a dynamic time warping (DTW) technique is used to enhance the similarity computation by taking the temporal distortion of similar audio segments into account. By processing the similarity matrix, we can obtain a coarse-grain music segmentation result. Finally, dynamic programming is applied to the coarse-grain segments so that a song can be decomposed into several major parts such as intro, verse, chorus, bridge and outro. The performance of the proposed music structure analysis system is demonstrated for pop and rock music.
© (2005) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yu Shiu, Hong Jeong, and C.-C. Jay Kuo "Musical structure analysis using similarity matrix and dynamic programming", Proc. SPIE 6015, Multimedia Systems and Applications VIII, 601516 (24 October 2005); https://doi.org/10.1117/12.633792
PROCEEDINGS
12 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

Musical examination to bridge audio data and sheet music
Proceedings of SPIE (March 05 2015)
Fast intra inter mode decision for H.264 encoding using a...
Proceedings of SPIE (November 01 2004)
Affine-transform-based image vector quantizer
Proceedings of SPIE (October 21 1993)
AutoDJ: the art of electronic music mixing
Proceedings of SPIE (October 24 2005)
Fast varying pitch tracking a new approach to speech...
Proceedings of SPIE (April 29 2007)

Back to Top