Modeling music and words using a multi-class naïve Bayes approach

We propose a query-by-text system for modeling a heterogeneous data set of music and words. We quantitatively show that our system can both annotate a novel song with semantically meaningful words and retrieve relevant unlabeled songs from a database given a text-based query. We explain two feature extraction methods useful for summarizing the audio content of a song. We describe a supervised multi-class naı̈ve Bayes model and compare two parameter estimation techniques. Our approach is influenced by recent computer vision research on the related tasks of image annotation and retrieval.