MaskBeat: Loopable Drum Beat Generation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lanzendörfer, Luca A., Grötschla, Florian, Galal, Karim, Wattenhofer, Roger
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908434205507584
author Lanzendörfer, Luca A.
Grötschla, Florian
Galal, Karim
Wattenhofer, Roger
author_facet Lanzendörfer, Luca A.
Grötschla, Florian
Galal, Karim
Wattenhofer, Roger
contents We present MaskBeat, a transformer-based approach for loopable drum pattern generation. Rather than predicting drum hits sequentially, our method uses bidirectional attention with iterative refinement, allowing instruments to be generated in parallel while maintaining musical coherence. Additionally, we introduce custom loss functions that capture drum-specific musical relationships. Our experiments show that MaskBeat generates higher quality and more musically coherent drum patterns than baseline approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2507_03395
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MaskBeat: Loopable Drum Beat Generation
Lanzendörfer, Luca A.
Grötschla, Florian
Galal, Karim
Wattenhofer, Roger
Sound
Audio and Speech Processing
We present MaskBeat, a transformer-based approach for loopable drum pattern generation. Rather than predicting drum hits sequentially, our method uses bidirectional attention with iterative refinement, allowing instruments to be generated in parallel while maintaining musical coherence. Additionally, we introduce custom loss functions that capture drum-specific musical relationships. Our experiments show that MaskBeat generates higher quality and more musically coherent drum patterns than baseline approaches.
title MaskBeat: Loopable Drum Beat Generation
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2507.03395