MRTB framework: a robust content-based music retrieval and browsing

In this paper, we propose new content-based music retrieval and browsing system so called MRTB. New feature extraction procedure such as multi-feature clustering (MFC) is proposed for robust and optimum performance of the music retrieval system. Using MFC, we can achieve 86% of average retrieving success rate and 0.5/spl sim/0.8 sec retrieval time based on top 10 ranked list rules. User friendly graphical interface of MRTB S/W is implemented in thumbnail manner so the user can easily verify their retrieving results with some useful musical information.