"Name That Song!": A Probabilistic Approach to Querying on Music and Text

By Eric Brochu

We present a novel, flexible statistical approach to modeling music and text jointly. The approach is based on multimodal mixture models and maximum a priori estimation. the learned models can be used to browse databases with documents containing music and text, to search for music using queries consisting of music and text (lyrics and other contextual information), to annotate text documents with music, and to automatically recommend or identify similar songs.

Back to the LCI Forum page