Title :
Extraction of High-Level Musical Structure From Audio Data and Its Application to Thumbnail Generation
Author :
Levy, Mark ; Sandler, Mark ; Casey, Michael
Author_Institution :
Centre for Digital Music, London Univ.
Abstract :
A method for segmenting musical audio with a hierarchical timbre model is introduced. New evidence is presented to show that music segmentation can be recast as clustering of timbre features, and a new clustering algorithm is described. A prototype thumbnail-generating application is described and evaluated. Experimental results are given, including comparison of machine and human segmentations
Keywords :
audio signal processing; feature extraction; audio data; hierarchical timbre model; high-level musical structure; musical audio segmentation; thumbnail generation; timbre features clustering; Algorithm design and analysis; Audio recording; Clustering algorithms; Cognition; Data mining; Educational institutions; Humans; Music information retrieval; Prototypes; Timbre;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on
Conference_Location :
Toulouse
Print_ISBN :
1-4244-0469-X
DOI :
10.1109/ICASSP.2006.1661200
