Algorithmic Composition of Melodies with Deep Recurrent Neural Networks

Abstract

A big challenge in algorithmic composition is to devise a model that is both easily trainable and able to reproduce the long-range temporal dependencies typical of music. Here we investigate how artificial neural networks can be trained on a large corpus of melodies and turned into automated music composers able to generate new melodies coherent with the style they have been trained on. We employ gated recurrent unit networks that have been shown to be particularly efficient in learning complex sequential activations with arbitrary long time lags. Our model processes rhythm and melody in parallel while modeling the relation between these two features. Using such an approach, we were able to generate interesting complete melodies or suggest possible continuations of a melody fragment that is coherent with the characteristics of the fragment itself.

arXiv commentProceeding of the 1st Conference on Computer Simulation of Musical Creativity, Huddersfield University

References in corpus (4)

• Adam: A Method for Stochastic Optimization
• Deep Learning in Neural Networks: An Overview
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation

Cited by in corpus (6)

• Exploring Variational Auto-Encoder Architectures, Configurations, and Datasets for Generative Music Explainable AI
• A Hierarchical Recurrent Neural Network for Symbolic Melody Generation
• Artificial Musical Intelligence: A Survey
• Computer Assisted Composition with Recurrent Neural Networks
• Artificial Neural Networks Jamming on the Beat
• Deep Segment Hash Learning for Music Generation