Output details
11 - Computer Science and Informatics
Royal Holloway, University of London
Return to search
Output 0 of 0 in the submission
Output title
A long-range self-similarity approach to segmenting DJ mixed music streams
Type
E - Conference contribution
Name of conference/published proceedings
Artificial Intelligence Applications and Innovations : Proceedings of the 9th IFIP WG 12.5 International Conference, AIAI 2013, Paphos, Cyprus, September 30 – October 2, 2013
Volume number
412
Issue number
-
First page of article
235
ISSN of proceedings
1868-4238
Year of publication
2013
Number of additional authors
2
Additional information
<24>This paper resolves the problem of reverse-engineering playlists from recordings of music programmes and finding (intentionally obfuscated) boundaries between different tracks. Quantitative analysis of trance music is difficult due to its self-similarity; existing methods of detecting transition points were thus not applicable. Therefore a new method based on optimisation reducing to dynamic programming has been developed.
Interdisciplinary
-
Cross-referral requested
-
Research group
B - Computer Learning Research Centre
Citation count
-
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-