Music information retrieval algorithm using time-frequency dictionaries

Abstract

In this paper, retrieving the required information from acoustic music signal in an efficient way is considered. The system is to determine similarities among songs, particularly, a piece of input music signal compared with storage music song's signal into the database and then to retrieve the similar song. Representing the music signal having sparse nature is accomplished by Matching Pursuit with time-frequency dictionaries. In order to match a candidate segment with the query segment, the music signal similarity measure is performed by Spatial Pyramid Matching. Evaluation results on music retrieval system illustrate that our music search system is better retrieval quality than such previous approaches. © 2011 Springer-Verlag.