Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.20426 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914286277754880 |
|---|---|
| author | Chu, Annie García, Hugo Flores Nieto, Oriol Salamon, Justin Pardo, Bryan Seetharaman, Prem |
| author_facet | Chu, Annie García, Hugo Flores Nieto, Oriol Salamon, Justin Pardo, Bryan Seetharaman, Prem |
| contents | 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 . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20426 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Mix2Morph: Learning Sound Morphing from Noisy Mixes Chu, Annie García, Hugo Flores Nieto, Oriol Salamon, Justin Pardo, Bryan Seetharaman, Prem Sound 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 . |
| title | Mix2Morph: Learning Sound Morphing from Noisy Mixes |
| topic | Sound |
| url | https://arxiv.org/abs/2601.20426 |