mlsanityData to 14 Oct 2026

Diff-Symbo: Text-Controlled Long-Duration Symbolic Music Generation Using Autoregressive Latent Diffusion Model

arXiv 2608.05222 ↗First posted 5 Aug 2026cs.SD eess.AScited by 0

On the map: Diffusion models → Audio, speech and music

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 24 of its 34 references that are in the map. First posted on arXiv 5 Aug 2026.

Builds on

24 of 34 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024Whole-Song Hierarchical Generation of Symbolic Music Using Cascaded Diffusion Models16 May
  2. 2024Long-form music generation with latent diffusion16 Apr
  3. 2023AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining10 Aug
  4. 2023MusicLDM: Enhancing Novelty in Text-to-Music Generation Using Beat-Synchronous Mixup Strategies3 Aug
  5. 2023Polyffusion: A Diffusion Model for Polyphonic Score Generation with Internal and External Controls19 Jul
  6. 2023Mousai: Text-to-Music Generation with Long-Context Latent Diffusion27 Jan
  7. 2021Symbolic Music Generation with Diffusion Models30 Mar

Other references · 17

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2017Neural Discrete Representation Learningcited by 4,712
  4. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  5. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  6. 2021SoundStream: An End-to-End Neural Audio Codeccited by 771
  7. 2024Lumiere: A Space-Time Diffusion Model for Video Generationcited by 455
  8. 2023Conditional Image-to-Video Generation with Latent Flow Diffusion Modelscited by 181
  9. 2024Fast Timing-Conditioned Latent Audio Diffusioncited by 181
  10. 2018A Hierarchical Latent Vector Model for Learning Long-Term Structure in Musiccited by 131
  11. 2020POP909: A Pop-song Dataset for Music Arrangement Generationcited by 83
  12. 2022Diffusion Probabilistic Models beat GANs on Medical Imagescited by 77
5 more
  1. 2021EMOPIA: A Multi-Modal Pop Piano Dataset For Emotion Recognition and Emotion-based Music Generationcited by 53
  2. 2023MuseCoco: Generating Symbolic Music from Textcited by 52
  3. 2022Symphony Generation with Permutation Invariant Language Modelcited by 35
  4. 2022Exploring the Efficacy of Pre-trained Checkpoints in Text-to-Music Generation Taskcited by 13
  5. 2024Multi-view MidiVAE: Fusing Track- and Bar-view Representations for Long Multi-track Symbolic Music Generationcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Efficient Long-Sequence Diffusion Modeling for Symbolic Music Generation
  2. 2025PhraseVAE and PhraseLDM: Latent Diffusion for Full-Song Multitrack Symbolic Music Generation
  3. 2025Conditional Diffusion as Latent Constraints for Controllable Symbolic Music Generation
  4. 2024Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generation
  5. 2024Why Perturbing Symbolic Music is Necessary: Fitting the Distribution of Never-used Notes through a Joint Probabilistic Diffusion Model
  6. 2023Composer Style-specific Symbolic Music Generation Using Vector Quantized Discrete Diffusion Models
  7. 2023Discrete Diffusion Probabilistic Models for Symbolic Music Generation
  8. 2025DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion