MaskBeat applies MaskGIT-style masked token prediction with drum-specific losses to generate loopable two-bar drum patterns, reporting higher hand-crafted metric scores than autoregressive baselines.
MaskBeat: Loopable Drum Beat Generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MaskBeat: Loopable Drum Beat Generation
MaskBeat applies MaskGIT-style masked token prediction with drum-specific losses to generate loopable two-bar drum patterns, reporting higher hand-crafted metric scores than autoregressive baselines.