Thinkit’s Submissions for Mirex2009 Audio Music Classification and Similarity Tasks

This full abstract describes our submitted systems for the MIREX09 audio classification tasks (genre, mood, classical composer, audio tagging) and music similarity and retrieval task. All the classification systems are based on basic acoustic features (e.g. MFCC) and the modeling framework of GSV-SVM, which has been successfully applied in speaker recognition field. And the similarity systems are based on a simple Euclid distance measurement on the mid-level features, which are also mapped from the basic acoustic features.