A diffusion SVS model with curriculum training and GRPO edits lyrics while preserving melody without manual alignment, outperforming Vevo2 on LyricEditBench.
Gtsinger: A global multi- technique singing corpus with realistic music scores for all singing tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
YingMusic-Singer: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance
A diffusion SVS model with curriculum training and GRPO edits lyrics while preserving melody without manual alignment, outperforming Vevo2 on LyricEditBench.