engleski

Challenges of Music Recommendation Software

In this paper, we present results of the analysis of a music identification application – Shazam Our aim was to discover if applications such as Shazam can improve organisational systems of performing rights organizations (PROs) in the area of precise monitoring of the songs used in the night club environment. The aim of the research was to evaluate how precise Shazam is in two different environments, the first one being a night club (where the music is loud and the signal to noise ratio is high) and the other one being home studio environment, where the signal to noise ratio is low. Each song was tagged for 10 seconds in two different environments and Shazam created two different audio fingerprints for each song based on some of the anchors of the simplified spectrogram and the target area between them. The conclusion is that Shazam application is not very accurate in the night club environment and, at this stage, cannot be used by performing rights organizations to monitor the music played in public spaces. In order for royalties to be collected and distributed correctly, one needs to have more precise instruments that offer the guarantee that music creators will get their due.

music recommendation software, music information retrieval, Shazam, Galaxy1, iPhone5, transaction cost theory, performing rights organizations

nije evidentirano