Abstract.A Musical Style Identification model based on Grammatical Inference (GI) is presented. Under this model, regular grammars are used for modeling Musical Style. Style Classification can be used to implement or improve content based retrieval in multimedia databases, musicology or music education. In this work, 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 provides a confidence value of a composition belonging to that grammar, which can be used to classify test melodies. A very important issue in this case is the use of a proper music coding scheme, so different coding schemes are presented and compared, achieving a 3 % classification error rate.
An application of Grammatical Inference (GI) in the field of Music Processing is presented, were Regular Grammars are used for modeling musical style. The interest in modeling musical style resides in the use of these models in applications, such as Automatic Composition and Automatic Musical Style Recognition. We have studied three GI Algorithms, which have been previously applied successfully in other fields. In this work, these algorithms have been used to learn a stochastic grammar for each of three different musical styles from examples of melodies. Then, each of the learned grammars was used to stochastically synthesize new melodies (Composition) or to classify test melodies (Style Recognition). Our previous studies in this field showed the need of a proper music coding scheme. Different coding schemes are presented and compared according to results in Composition and Style Recognition. Results from previous studies have been improved.
Musical Style Identification (MSI) aims to automatically classify music by style. It is being recently explored, mostly in the field of multimedia databases, with potential applications to content-based retrieval. But MSI may be also employed in other applications. We try to face up this challenge with two different methodologies: n-gram Models and Neural Networks. Very good results were obtained with n-grams in our previous research and we were willing to test how other Artificial Intelligence techniques performed with this task, so we began a preliminary study with Multilayer Perceptrons that is promising.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations –citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.