Artificial Neural Networks Jamming on the Beat
This work addresses a specific problem in music generation for AI applications, offering an incremental improvement by simplifying the process to enhance structural coherence in generated songs.
The paper tackles the challenge of generating symbolic music with long-scale correlations by proposing a two-step approach: first generating drum patterns as a foundation, then using them to guide melody generation with a simple neural network, resulting in music with improved long-scale note correlations.
This paper addresses the issue of long-scale correlations that is characteristic for symbolic music and is a challenge for modern generative algorithms. It suggests a very simple workaround for this challenge, namely, generation of a drum pattern that could be further used as a foundation for melody generation. The paper presents a large dataset of drum patterns alongside with corresponding melodies. It explores two possible methods for drum pattern generation. Exploring a latent space of drum patterns one could generate new drum patterns with a given music style. Finally, the paper demonstrates that a simple artificial neural network could be trained to generate melodies corresponding with these drum patters used as inputs. Resulting system could be used for end-to-end generation of symbolic music with song-like structure and higher long-scale correlations between the notes.