The paper describes a new database, which currently consists of 64 songs encompassing approximately 6600 notes, and a system, which uses Variable-Length Markov Models (VLMM) to predict the melodies in the uzun hava (long tune) form, a melodic structure in Turkish folk music. The work shows VLMMs are highly predictive. This suggests that variable-length Markov models (VLMMs) may be applied to makam-based and non-metered musical forms, in addition to Western musical traditions. To the best of our knowledge, the work presents the first symbolic, machine readable database of uzun havas and the first application of predictive modeling in Turkish folk music. © 2011 International Society for Music Information Retrieval.
CITATION STYLE
Şentürk, S., & Chordia, P. (2011). Modeling melodic improvisation in turkish folk music using variable-length markov models. In Proceedings of the 12th International Society for Music Information Retrieval Conference, ISMIR 2011 (pp. 269–274).
Mendeley helps you to discover research relevant for your work.