Rule-generated preference data aligned via sequential DPO and KTO reduces musical constraint violations and improves coherence in lyric-to-melody generation over baselines.
Seed-music: A unified frame- work for high quality and controlled music generation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
LaDA-Band applies discrete masked diffusion with dual-track conditioning and progressive training to generate vocal-to-accompaniment tracks that improve acoustic authenticity, global coherence, and dynamic orchestration over prior baselines.
citing papers explorer
-
Aligning Language Models for Lyric-to-Melody Generation with Rule-Based Musical Constraints
Rule-generated preference data aligned via sequential DPO and KTO reduces musical constraint violations and improves coherence in lyric-to-melody generation over baselines.
-
LaDA-Band: Language Diffusion Models for Vocal-to-Accompaniment Generation
LaDA-Band applies discrete masked diffusion with dual-track conditioning and progressive training to generate vocal-to-accompaniment tracks that improve acoustic authenticity, global coherence, and dynamic orchestration over prior baselines.