In this paper we propose a novel approach for contentbased music recommendation. The main innovation of the proposed technique consists of a similarity function that, instead of considering entire songs or their thumbnail representations, analyzes audio similarities between semantic segments from different audio tracks. The rationale of our idea is that a song similarity and recommendation technique, to be more meaningful to the user from a semantic point of view, may evaluate and exploit similarities on semantic units between audio tracks. Our similarity algorithm consists of two main stages: the first step performs segmentation of the song in semantic parts. The latter assigns a similarity and recommendation score to a pair of songs, by computing the distance between the representations of their segments. To assign the global similarity and recommendation score, we consider a consistent subset of all the inter-segment distances. By adopting a graph-bases framework, we propose a graph-reduction algorithm on weighted edges that connect segments of different songs to optimize the similarity score with respect to our recommendation goal. Experiments conducted on a database of 200 audio tracks of various authors and genres show promising results.

Original languageEnglish
Title of host publicationProceedings of the IASTED International Conference on Internet and Multimedia Systems and Applications and Visual Communications
Pages182-187
Number of pages6
Publication statusPublished - 2008
Externally publishedYes
EventIASTED International Conference on Internet and Multimedia Systems and Applications and Visual Communications - Innsbruck, Austria
Duration: 17 Mar 200818 Mar 2008

Conference

ConferenceIASTED International Conference on Internet and Multimedia Systems and Applications and Visual Communications
CountryAustria
CityInnsbruck
Period17/03/0818/03/08

    Research areas

  • Content-based multimedia retrieval, Genre classification, Music recommendation

ID: 36755409