The increase of the quantity of user-generated content experienced in socialmedia has boosted the importance of analysing and organising the content by itsquality. Here, we propose a method that uses audio fingerprinting to organiseand infer the quality of user-generated audio content. The proposed methoddetects the overlapping segments between different audio clips to organise andcluster the data according to events, and to infer the audio quality of thesamples. A test setup with concert recordings manually crawled from YouTube isused to validate the presented method. The results show that the proposedmethod achieves better results than previous methods.
展开▼