Sciweavers

Share
SIGIR
2005
ACM

An industrial-strength content-based music recommendation system

11 years 5 months ago
An industrial-strength content-based music recommendation system
We present a metadata free system for the interaction with massive collections of music, the MusicSurfer. MusicSurfer automatically extracts descriptions related to instrumentation, rhythm and harmony from music audio signals. Together with efficient similarity metrics, the descriptions allow navigation of multimillion track music collections in a flexible and efficient way without the need of metadata or human ratings. Categories and Subject Descriptors H.5.5 [Information Interfaces and Presentation]: Sound and Music Computing – signal analysis, synthesis, and processing, systems. General Terms Algorithms Keywords Music content management, music information retrieval, contentbased audio retrieval, music recommendation. Nowadays access to online music is possible by querying artist or song names (or other types of editorial data such as genre), or by browsing recommendations generated by collaborative filtering , i.e. using recommender systems that exploit information of the type &q...
Pedro Cano, Markus Koppenberger, Nicolas Wack
Added 26 Jun 2010
Updated 26 Jun 2010
Type Conference
Year 2005
Where SIGIR
Authors Pedro Cano, Markus Koppenberger, Nicolas Wack
Comments (0)
books