SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908605235593216 |
|---|---|
| author | Yang, Chenyu Wang, Shuai Chen, Hangting Tan, Wei Yu, Jianwei Li, Haizhou |
| author_facet | Yang, Chenyu Wang, Shuai Chen, Hangting Tan, Wei Yu, Jianwei Li, Haizhou |
| contents | Generating music with coherent structure, harmonious instrumental and vocal elements remains a significant challenge in song generation. Existing language models and diffusion-based methods often struggle to balance global coherence with local fidelity, resulting in outputs that lack musicality or suffer from incoherent progression and mismatched lyrics. This paper introduces $\textbf{SongBloom}$, a novel framework for full-length song generation that leverages an interleaved paradigm of autoregressive sketching and diffusion-based refinement. SongBloom employs an autoregressive diffusion model that combines the high fidelity of diffusion models with the scalability of language models. Specifically, it gradually extends a musical sketch from short to long and refines the details from coarse to fine-grained. The interleaved generation paradigm effectively integrates prior semantic and acoustic context to guide the generation process. Experimental results demonstrate that SongBloom outperforms existing methods across both subjective and objective metrics and achieves performance comparable to the state-of-the-art commercial music generation platforms. Audio samples are available on our demo page: https://cypress-yang.github.io/SongBloom_demo. The code and model weights have been released on https://github.com/Cypress-Yang/SongBloom . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_07634 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement Yang, Chenyu Wang, Shuai Chen, Hangting Tan, Wei Yu, Jianwei Li, Haizhou Audio and Speech Processing Multimedia Generating music with coherent structure, harmonious instrumental and vocal elements remains a significant challenge in song generation. Existing language models and diffusion-based methods often struggle to balance global coherence with local fidelity, resulting in outputs that lack musicality or suffer from incoherent progression and mismatched lyrics. This paper introduces $\textbf{SongBloom}$, a novel framework for full-length song generation that leverages an interleaved paradigm of autoregressive sketching and diffusion-based refinement. SongBloom employs an autoregressive diffusion model that combines the high fidelity of diffusion models with the scalability of language models. Specifically, it gradually extends a musical sketch from short to long and refines the details from coarse to fine-grained. The interleaved generation paradigm effectively integrates prior semantic and acoustic context to guide the generation process. Experimental results demonstrate that SongBloom outperforms existing methods across both subjective and objective metrics and achieves performance comparable to the state-of-the-art commercial music generation platforms. Audio samples are available on our demo page: https://cypress-yang.github.io/SongBloom_demo. The code and model weights have been released on https://github.com/Cypress-Yang/SongBloom . |
| title | SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement |
| topic | Audio and Speech Processing Multimedia |
| url | https://arxiv.org/abs/2506.07634 |