Open Access
A Novel Method of Music Generation Based on Three Different Recurrent Neural Networks
Author(s) -
Jiatong Xie
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1549/4/042034
Subject(s) - midi , generative grammar , computer science , recurrent neural network , task (project management) , encoding (memory) , artificial intelligence , deep learning , simple (philosophy) , field (mathematics) , artificial neural network , adversarial system , speech recognition , machine learning , engineering , mathematics , philosophy , systems engineering , epistemology , pure mathematics , operating system
manuscripts Nowadays, music generation has become an important research field in the study of deep learning. Many different methods such as Generative Adversarial Networks (GAN) and Variational self-encoding (VAE) are already proved to be able to handle such task. In this paper, RNNs, such as LSTM and GRU, will be used to compose the core of the network to predict notes of the melody and generate new music. MIDI will be used as the general music format because of its simple and appropriate data structure that can be coded as a dictionary.