Metraipolis › archive › dc_044467168911
Diff-Symbo: Text-Controlled Long-Duration Symbolic Music Generation Using Autoregressive Latent Diffusion Model — arXiv:2608.05222
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.05222
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:10:28.818Z
- SHA-256 of the archived text
cdb0e3e99790f7b21897df87e9d00dfaeb41213724b31f496ae897b934e36e40- Stable URL of this page
https://metraipolis.com/documento/dc_044467168911
How to cite
Diff-Symbo: Text-Controlled Long-Duration Symbolic Music Generation Using Autoregressive Latent Diffusion Model — arXiv:2608.05222 — arXiv (en), https://arxiv.org/abs/2608.05222 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_044467168911 (Metraipolis archive dc_044467168911, sha256 cdb0e3e99790f7b21897df87e9d00dfaeb41213724b31f496ae897b934e36e40)
BibTeX
@misc{dc044467168911,
title = {Diff-Symbo: Text-Controlled Long-Duration Symbolic Music Generation Using Autoregressive Latent Diffusion Model — arXiv:2608.05222},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.05222},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_044467168911; sha256 cdb0e3e99790f7b21897df87e9d00dfaeb41213724b31f496ae897b934e36e40},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05222. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Text-controlled symbolic music generation has recently gained research attention due to its versatile, flexible and straightforward approach to music composition. However, previous approaches tend to generate symbolic music with compromising quality, diversity, controllability and limited duration. In this paper, we present Diff-Symbo, an innovative method that uses latent diffusion model (LDM) to generate high-quality, diverse and long-duration symbolic music. To address the lack of text-symbolic music dataset, we develop a comprehensive dataset with 19,345 text templates by employing large language model. Furthermore, we design a music information encoder to reduce the training overhead while extracting more effective control representations. Given textual descriptions, our proposed method leverages LDM to improve the quality and diversity of music generation. Our method also improves the duration and the compositional consistency of music generation through an autoregressive approach. Experimental results show significant improvements of Diff-Symbo in text controllability, duration, and the quality of generated music compared to the baseline models such as GPT-4, MuseCoco and Multitrack Music Transformer (MMT). As one of the pioneer models in this field, Diff-Symbo paves the way towards controllable and high-quality symbolic music composition based on LDM, offering valuable contributions to both music amateurs and practitioners. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-07 in eess.AS). Categorie arXiv: Sound (cs.SD) ; Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2608.05222 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-31T11:00:09.970Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).