Deep learning for Turkish makam music composition

In this paper, we introduce a new deep-learning-based system that can compose structured Turkish makam music (TMM) in the symbolic domain. Presented artificial TMM composer (ATMMC) takes eight initial notes from human user and completes rest of piece. The backbone consists multilayered long short-term memory (LSTM) networks. ATMMC create pieces Hicaz Nihavent makams ?ark? form, which be viewed played with Mus2, notation software for microtonal music. Statistical analysis shows composed by are approximately 84% similar to training data. is an open-source project assist enthusiasts creating professional, educational, or entertainment purposes.