mlsanityData to 14 Oct 2026

Diff2Mix: Controllable Music Mixing via Diffusion Models and Differentiable Audio Effects

arXiv 2608.05442 ↗First posted 5 Aug 2026eess.AS cs.SDcited by 0

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

Abstract (arXiv)

Automatic music mixing aims to combine multitrack recordings into a balanced and coherent musical piece. Because the content of different songs and the subjective preferences of mixing engineers jointly shape the final outcome, a practical system should deliver well-balanced mixes while allowing for controllable stylistic variation. However, most existing methods treat automatic mixing and mixing style control as separate tasks, making it difficult for a single system to produce high-quality mixes while remaining editable and style-aware. To address this limitation, this paper presents Diff2Mix, a generative automatic mixing system based on diffusion models and a differentiable mixing console. This system offers two levels of optional user control: a reference audio enables overall production style control, and the differentiable mixing console provides explicit audio effects parameters for interpretability and fine-grained optimization. We demonstrate our system's competitive performance through both objective and subjective evaluations in terms of mixing quality and control ability. We provide code and audio samples at our project page https://zys711.github.io/Diff2Mix .

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 42 references that are in the map. First posted on arXiv 5 Aug 2026.

Builds on

24 of 42 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Audio synthesizer inversion in symmetric parameter spaces with approximately equivariant flow matching8 Jun

Other references · 23

  1. 2022Scalable Diffusion Models with Transformerscited by 6,054
  2. 2022Classifier-Free Diffusion Guidancecited by 5,847
  3. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  4. 2022Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentationcited by 719
  5. 2018Neural Autoregressive Flowscited by 208
  6. 2020DDSP: Differentiable Digital Signal Processingcited by 178
  7. 2021Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpuscited by 60
  8. 2023Moisesdb: A dataset for source separation beyond 4-stemscited by 39
  9. 2020Automatic multitrack mixing with a differentiable mixing console of neural audio effectscited by 27
  10. 2025KAD: No More FAD! An Effective and Efficient Evaluation Metric for Audio Generationcited by 24
  11. 2022Style Transfer of Audio Effects with Differentiable Signal Processingcited by 18
  12. 2022Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio Effectscited by 18
11 more
  1. 2021Filtered Noise Shaping for Time Domain Room Impulse Response Estimation From Reverberant Speechcited by 16
  2. 2018InverSynth: Deep Estimation of Synthesizer Parameter Configurations from Audio Signalscited by 11
  3. 2022Automatic music mixing with deep learning and out-of-domain datacited by 11
  4. 2024Text2FX: Harnessing CLAP Embeddings for Text-Guided Audio Effectscited by 9
  5. 2021Direct design of biquad filter cascades with deep learning by sampling random polynomialscited by 8
  6. 2024ST-ITO: Controlling Audio Effects for Style Transfer with Inference-Time Optimizationcited by 7
  7. 2022End-to-end Music Remastering System Using Self-supervised and Adversarial Trainingcited by 6
  8. 2024Diff-MST: Differentiable Mixing Style Transfercited by 6
  9. 2025Fx-Encoder++: Extracting Instrument-Wise Audio Effects Representations from Mixturescited by 6
  10. 2025Automatic Music Mixing using a Generative Model of Effect Embeddingscited by 3
  11. 2025LLM2Fx-Tools: Tool Calling For Music Post-Productioncited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Controllable Music Production with Diffusion Models and Guidance Gradients
  2. 2024Diff-A-Riff: Musical Accompaniment Co-creation via Latent Diffusion Models
  3. 2024Bass Accompaniment Generation via Latent Diffusion
  4. 2025Diff-TONE: Timestep Optimization for iNstrument Editing in Text-to-Music Diffusion Models
  5. 2024Combining audio control and style transfer using latent diffusion
  6. 2024Editing Music with Melody and Text: Using ControlNet for Diffusion Transformer
  7. 2023Polyffusion: A Diffusion Model for Polyphonic Score Generation with Internal and External Controls
  8. 2026Rethinking Automatic Music Mixing as Sequential Stem Blending ↗