Towards Unified Song Generation and Singing Voice Conversion with Accompaniment Co-Generation
This work addresses the isolation between song generation and SVC by providing a unified framework that enables cross-task timbre control and vocal-accompaniment synergy, benefiting music production and AI research.
UniSinger unifies song generation and singing voice conversion (SVC) in a single end-to-end framework, enabling zero-shot speaker cloning and accompaniment co-generation. It achieves state-of-the-art performance on both tasks, with complementary benefits for intelligent music production.
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.