Paper ID: 2306.06284

Everybody Compose: Deep Beats To Music

Conghao Shen, Violet Z. Yao, Yixin Liu

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.

Submitted: Jun 9, 2023