Effects of Album and Artist Filters in Audio Similarity Computed for Very Large Music Databases

In music information retrieval, one of the central goals is to automatically recommend music to users based on a query song or query artist. In this study, a very large data set (over 250,000 songs) containing multiple albums from individual artists was analyzed. Results show that artist effect does...

Full description

Saved in:
Bibliographic Details
Published inComputer music journal Vol. 34; no. 3; pp. 20 - 28
Main Authors Flexer, Arthur, Schnitzer, Dominik
Format Journal Article
LanguageEnglish
Published 55 Hayward St., Cambridge, MA 02142-1315, USA MIT Press 01.09.2010
The MIT Press
MIT Press Journals, The
Subjects
Artists
Computation
Computer music
Data lines
Datasets
Digital music
Geometric lines
Information retrieval
Music
Music Information Retrieval
Music instrumentation
Musical improvisation
Musical performance
Musical recordings
Musicians & conductors
Online data bases
Recommendations
Searches
Similarity
Sound filters
Online AccessGet full text

Cover

More Information
Summary:In music information retrieval, one of the central goals is to automatically recommend music to users based on a query song or query artist. In this study, a very large data set (over 250,000 songs) containing multiple albums from individual artists was analyzed. Results show that artist effect does exist in very large databases, and the album effect is bigger than the artist effect.
Bibliography:Fall, 2010
ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0148-9267
1531-5169
DOI:10.1162/COMJ_a_00004