Mix2Morph: Learning Sound Morphing from Noisy Mixes

TL;DR

Mix2Morph is a novel diffusion-based model that performs sound morphing and infusions without requiring dedicated datasets, enabling more controllable sound design through stable, perceptually coherent transformations.

Contribution

It introduces a fine-tuned diffusion model that achieves sound morphing from noisy mixes, advancing sound infusions without specialized datasets.

Findings

Outperforms prior baselines in objective evaluations

Produces high-quality sound infusions across diverse categories

Enables stable and perceptually coherent sound morphs

Abstract

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 .