While song generation and singing voice conversion (SVC) have evolved significantly, they have long been developed isolated: the former lacks zero-shot speaker cloning, while the latter overlooks vocal-accompaniment synergy. To bridge this gap, we propose UniSinger, the first end-to-end framework unifying speaker cloning song generation and accompaniment co-generation SVC. Building on the multimodal diffusion transformer, we construct a unified speaker embedding space transferring speaker representation from SVC to song generation, endowing fine-grained cross-task timbre control. To mitigate multi-task optimization conflicts, we design a curriculum learning strategy using task-specific modality masking to guide the model to gradually master the generative mechanisms among semantic content, vocal timbre, and accompaniment. Experiments show state-of-the-art performance on both tasks and realizes complementary benefits, offering new possibilities for intelligent music production.

翻译：虽然歌曲生成和歌声转换（SVC）已取得显著进展，但两者长期处于孤立发展状态：前者缺乏零样本说话人克隆能力，后者则忽视了人声与伴奏的协同性。为弥合这一差距，我们提出UniSinger——首个统一说话人克隆歌曲生成与伴奏协同生成SVC的端到端框架。基于多模态扩散Transformer，我们构建了统一说话人嵌入空间，将SVC中的说话人表征迁移至歌曲生成，实现跨任务细粒度音色控制。为缓解多任务优化冲突，我们设计了一种课程学习策略，通过任务特定模态掩码引导模型逐步掌握语义内容、人声音色与伴奏之间的生成机制。实验表明，本方法在两项任务上均达到最优性能，并实现互补增益，为智能音乐制作提供了新可能。