Everybody Compose: Deep Beats To Music

06/09/2023

∙

by   Conghao Shen, et al.

∙

0

∙

share

This project presents a deep learning approach to generate monophonic melodies based on input beats, allowing even amateurs to create their own music compositions. Three effective methods - LSTM with Full Attention, LSTM with Local Attention, and Transformer with Relative Position Representation - are proposed for this novel task, providing great variation, harmony, and structure in the generated music. This project allows anyone to compose their own music by tapping their keyboards or “recoloring” beat sequences from existing works.