Everybody Compose: Deep Beats To Music

Conghao Shen, Violet Z. Yao, Yixin Liu
6/9/2023
cs.SDcs.LGcs.MM

No official code found. Best implementation: tsunrise/everybody-compose (12 stars, MIT, last commit 2023-04-12).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

tsunrise/everybody-composeCommunity100%
MIT

Everybody Compose: Deep Beats To Music

122Shell, PythonOct 15, 20223 years agoMIT

Similar Papers

Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano Compositions

83% match1 repo6042020

A Novel Bi-LSTM And Transformer Architecture For Generating Tabla Music

82% match2024

StemGen: A music generation model that listens

82% match1 repo352023

A Survey of Music Generation in the Context of Interaction

81% match2024

Music transcription modelling and composition using deep learning

81% match1 repo3412016

SynthScribe: Deep Multimodal Tools for Synthesizer Sound Retrieval and Exploration

81% match2023

Cite this paper

@article{shen2023everybody,
  title  = {Everybody Compose: Deep Beats To Music},
  author = {Conghao Shen and Violet Z. Yao and Yixin Liu},
  year   = {2023},
  eprint = {2306.06284},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.06284v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.06284.svg)](https://codeofpaper.com/paper/2306.06284)

Discussion