Instrument Separation of Symbolic Music by Explicitly Guided Diffusion Model
On the map: Diffusion models → Audio, speech and music
Abstract (arXiv)
Similar to colorization in computer vision, instrument separation is to assign instrument labels (e.g. piano, guitar...) to notes from unlabeled mixtures which contain only performance information. To address the problem, we adopt diffusion models and explicitly guide them to preserve consistency between mixtures and music. The quantitative results show that our proposed model can generate high-fidelity samples for multitrack symbolic music with creativity.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 9 of its 11 references that are in the map. First posted on arXiv 5 Sep 2022.
Builds on
9 of 11 references.
Closest ancestors · 1
Same direction, newest first
Other references · 8
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2020Denoising Diffusion Implicit Modelscited by 9,655
- 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
- 2022Classifier-Free Diffusion Guidancecited by 5,717
- 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,552
- 2017MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompanimentcited by 151
- 2018Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generationcited by 20
- 2021Towards Automatic Instrumentation by Learning to Separate Parts in Symbolic Multitrack Musiccited by 5
Built on by
Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 1.
2 papers.
- 2022A Survey on Generative Diffusion Modelcited by 238
- 2025On the de-duplication of the Lakh MIDI datasetcited by 1
- 2025On the de-duplication of the Lakh MIDI dataset20 Sep 2025
- 2022A Survey on Generative Diffusion Model6 Sep 2022
Similar, not cited
Close in wording, no citation either way
- 2023DiffuseRoll: Multi-track multi-category music generation based on diffusion model
- 2025Mamba-Diffusion Model with Learnable Wavelet for Controllable Symbolic Music Generation
- 2023Generating symbolic music using diffusion models
- 2023Polyffusion: A Diffusion Model for Polyphonic Score Generation with Internal and External Controls
- 2025User-guided Generative Source Separation
- 2024Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generation
- 2023Multi-Source Diffusion Models for Simultaneous Music Generation and Separation
- 2023Discrete Diffusion Probabilistic Models for Symbolic Music Generation