Modeling musical style using grammatical inference techniques: a tool for classifying and generating melodies

An application of grammatical inference (GI) in the field of music processing is presented, where regular grammars are used for modeling musical style. These models can be used to generate (automatic composition) and classify music by style (musical style identification), with their resulting applications. The latter, for instance, would improve content based retrieval in multimedia databases, joining indexing by musical style to other suitable indexes. Several GI techniques are used to learn, from examples of melodies, a stochastic grammar for each of three different musical styles. Then, each of the learned grammars is used to synthesize new melodies (composition) or to classify test melodies (style identification). Our studies in this field show the need of a proper music coding scheme, so different coding schemes are presented and compared. Results from previous studies have been improved, achieving in style identification a 97% success rate.