Title :
Automatic structure detection for popular music
Author :
Maddage, Namunu C.
Author_Institution :
Inst. for Infocomm Res., Singapore, Singapore
Abstract :
Our proposed approach detects music structures by looking at beat-space segmentation, chords, singing-voice boundaries, and melody- and content-based similarity regions. Experiments illustrate that the proposed approach is capable of extracting useful information for music applications.
Keywords :
multimedia systems; music; automatic music structure detection; beat-space segmentation; chords; content-based similarity region; melody-based similarity region; singing-voice boundaries; Bars; Data mining; Fluctuations; Frequency measurement; Harmonic analysis; Instruments; Multiple signal classification; Pulse measurements; Size measurement; Transient analysis; content-based; octaves; segmentation; subbands; voice boundaries;
Journal_Title :
MultiMedia, IEEE
DOI :
10.1109/MMUL.2006.3
