mlsanityData to 14 Oct 2026

Everybody Compose: Deep Beats To Music

arXiv 2306.06284 ↗First posted 9 Jun 2023cs.SD cs.LG cs.MMcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 8 of its 18 references that are in the map. First posted on arXiv 9 Jun 2023.

Builds on

8 of 18 references.

References · 8

  1. 2017Attention Is All You Needcited by 60,361
  2. 2022Generative Adversarial Networkscited by 5,627
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  4. 2018Self-Attention with Relative Position Representationscited by 1,120
  5. 2018Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Datasetcited by 217
  6. 2018Music Transformercited by 211
  7. 2018SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesiscited by 81
  8. 2016Text-based LSTM networks for Automatic Music Compositioncited by 6

Built on by

Not cited yet.