# Mix2Morph: Learning Sound Morphing from Noisy Mixes

arXiv: https://arxiv.org/abs/2601.20426 · HTML: https://mlsanity.com/paper/2601.20426/

## 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.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 14 of 14)

- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://mlsanity.com/paper/2308.05734/) (2023)
- [Long-form music generation with latent diffusion](https://mlsanity.com/paper/2404.10301/) (2024)
- [Sketch2Sound: Controllable Audio Generation via Time-Varying Signals and Sonic Imitations](https://mlsanity.com/paper/2412.08550/) (2024)
- [FLAM: Frame-Wise Language-Audio Modeling](https://mlsanity.com/paper/2505.05335/) (2025)
- [Ambient Diffusion Omni: Training Good Models with Bad Data](https://mlsanity.com/paper/2506.10038/) (2025)
- [Neural Granular Sound Synthesis](https://mlsanity.com/paper/2008.01393/) (2020)
- [Towards Controllable Audio Texture Morphing](https://mlsanity.com/paper/2304.11648/) (2023)
- [MorphFader: Enabling Fine-grained Controllable Morphing with Text-to-Audio Models](https://mlsanity.com/paper/2408.07260/) (2024)
- [SoundMorpher: Perceptually-Uniform Sound Morphing with Diffusion Model](https://mlsanity.com/paper/2410.02144/) (2024)
- [The Concatenator: A Bayesian Approach To Real Time Concatenative Musaicing](https://mlsanity.com/paper/2411.04366/) (2024)
- [Latent Granular Resynthesis using Neural Audio Codecs](https://mlsanity.com/paper/2507.19202/) (2025)
- [CAESynth: Real-Time Timbre Interpolation and Pitch Control with Conditional Autoencoders](https://mlsanity.com/paper/2111.05174/) (2021)
- [Learning Perceptually Relevant Temporal Envelope Morphing](https://mlsanity.com/paper/2506.01588/) (2025)

## 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 .