Multi-theme analysis of music emotion similarity for jukebox application

Chih Yi Lin, Stone Cheng*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

This study proposes a music linkage jukebox system that recommends listeners a ranked list retrieved by the resemblance of music-induced emotions between the query clip and music bank. The retrieval results also provide a time-varying interface of dynamic emotional transition caused by music in a predetermined emotion plane. In the system, the multi-theme phrases of musical structure, including Intro, Verse, and the Chorus are analyzed by autocorrelation function as an input test structure, then using feature-weighted scoring algorithms to analyze the ingredients of music emotion with five audio characteristics sets of the testing music clips. The similarity of emotions between music clips and music bank are measured by Euclidean distance algorithms. Preliminary evaluations of the system illustrate the novelty with the emotion ratios and the real-time emotion locus evoked by music clips. The proposed system also shows the rapid browsing in the process for emotion similarity of music retrieval.

Original languageEnglish
Title of host publicationICALIP 2012 - 2012 International Conference on Audio, Language and Image Processing, Proceedings
Pages241-246
Number of pages6
DOIs
StatePublished - 1 Dec 2012
Event2012 3rd IEEE/IET International Conference on Audio, Language and Image Processing, ICALIP 2012 - Shanghai, China
Duration: 16 Jul 201218 Jul 2012

Publication series

NameICALIP 2012 - 2012 International Conference on Audio, Language and Image Processing, Proceedings

Conference

Conference2012 3rd IEEE/IET International Conference on Audio, Language and Image Processing, ICALIP 2012
CountryChina
CityShanghai
Period16/07/1218/07/12

Fingerprint Dive into the research topics of 'Multi-theme analysis of music emotion similarity for jukebox application'. Together they form a unique fingerprint.

Cite this