mlsanityData to 14 Oct 2026

Mix2Morph: Learning Sound Morphing from Noisy Mixes

arXiv 2601.20426 ↗First posted 28 Jan 2026cs.SDcited by 0

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

Abstract (arXiv)

We introduce Mix2Morph, a text-to-audio diffusion model fine-tuned to perform sound morphing without a dedicated dataset of morphs. By finetuning on noisy surrogate mixes at higher diffusion timesteps, Mix2Morph yields stable, perceptually coherent morphs that convincingly integrate qualities of both sources. We specifically target sound infusions, a practically and perceptually motivated subclass of morphing in which one sound acts as the dominant primary source, providing overall temporal and structural behavior, while a secondary sound is infused throughout, enriching its timbral and textural qualities. Objective evaluations and listening tests show that Mix2Morph outperforms prior baselines and produces high-quality sound infusions across diverse categories, representing a step toward more controllable and concept-driven tools for sound design. Sound examples are available at https://anniejchu.github.io/mix2morph .

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 14 of its 28 references that are in the map. First posted on arXiv 28 Jan 2026.

Builds on

14 of 28 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024SoundMorpher: Perceptually-Uniform Sound Morphing with Diffusion Model3 Oct
  2. 2024Long-form music generation with latent diffusion16 Apr
  3. 2023AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining10 Aug

Other references · 11

  1. 2023High-Fidelity Audio Compression with Improved RVQGANcited by 431
  2. 2024Sketch2Sound: Controllable Audio Generation via Time-Varying Signals and Sonic Imitationscited by 24
  3. 2025FLAM: Frame-Wise Language-Audio Modelingcited by 18
  4. 2025Ambient Diffusion Omni: Training Good Models with Bad Datacited by 18
  5. 2020Neural Granular Sound Synthesiscited by 4
  6. 2023Towards Controllable Audio Texture Morphingcited by 4
  7. 2024MorphFader: Enabling Fine-grained Controllable Morphing with Text-to-Audio Modelscited by 4
  8. 2024The Concatenator: A Bayesian Approach To Real Time Concatenative Musaicingcited by 2
  9. 2025Latent Granular Resynthesis using Neural Audio Codecscited by 2
  10. 2021CAESynth: Real-Time Timbre Interpolation and Pitch Control with Conditional Autoencoderscited by 1
  11. 2025Learning Perceptually Relevant Temporal Envelope Morphingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Smorph: Playable Sound Morphing with Diffusion Models
  2. 2025AudioMorphix: Training-free audio editing with diffusion probabilistic models
  3. 2025Audio Palette: A Diffusion Transformer with Multi-Signal Conditioning for Controllable Foley Synthesis
  4. 2026Diffusion Timbre Transfer Via Mutual Information Guided Inpainting
  5. 2026DDSynth-RL: Audio Synthesizer Inversion via Discrete Diffusion with Reinforcement Learning
  6. 2026Stage-adaptive audio diffusion modeling
  7. 2025Score Distillation Sampling for Audio: Source Separation, Synthesis, and Beyond
  8. 2023EDMSound: Spectrogram Based Diffusion Models for Efficient and High-Quality Audio Synthesis