2024-03-28T11:50:11Zhttp://digital.csic.es/dspace-oai/requestoai:digital.csic.es:10261/1253692020-01-17T10:03:20Zcom_10261_60com_10261_4col_10261_439
Melodic pattern extraction in large collections of music recordings using time series mining techniques
Demo session,15th International Society for Music Information Retrieval Conference (ISMIR 2014), October 27 - 31, 2014 Taipei, Taiwan.
Gulati, Sankalp
Serra, Joan
Ishwar, Vignesh
Serra, Xavier
Melodic patterns
Melodic similarity
Carnatic
We demonstrate a data-driven unsupervised approach for the discovery of melodic patterns in large collections of Indian art music recordings. The approach first works on single recordings and subsequently searches in the entire music collection. Melodic similarity is based on dynamic time warping. The task being computationally intensive, lower bounding and early abandoning techniques are applied during distance computation. Our dataset comprises 365 hours of music, containing 1,764 audio recordings representing the melodic diversity of Carnatic music. A preliminary evaluation based on expert feedback on a subset of the music collection shows encouraging results. In particular, several musically interesting relationships are discovered, yielding further scope for establishing novel similarity measures based on melodic patterns.
Peer reviewed
2015-11-19T17:15:23Z
2015-11-19T17:15:23Z
2014-10-27
presentación
http://hdl.handle.net/10261/125369
en
Postprint
http://www.terasoft.com.tw/conf/ismir2014/LBD%5CLBD22.pdf
SÃ
open
International Society for Music Information Retrieval