Smorph: Playable Sound Morphing with Diffusion Models

2026-10-05

AI Summary

This work addresses the inability of existing diffusion models to disentangle temporal structure from timbral identity in sound morphing by proposing a training-free guidance framework. Its core innovation is a novel "structure anchoring" mechanism that strictly preserves the temporal characteristics of the source audio while independently transforming its timbre, thereby supporting multimodal conversions including prompt-to-prompt, audio-to-prompt, and audio-to-audio. Experimental results demonstrate that the proposed method significantly improves temporal structural fidelity and source signal preservation. Furthermore, evaluations conducted by professional musicians confirm that the generated smooth morphing trajectories exhibit outstanding expressiveness and playability.

Abstract

Sound morphing, generating intermediate sounds that transition from one sonic identity to another, can be a powerful tool for musical sound design. Existing diffusion-based morphing approaches entangle temporal structure and timbral identity, offering no mechanism to hold one fixed while transforming the other. We present smorph, a training-free guidance framework that preserves how a sound behaves over time while transforming what the sound is, allowing users to morph, for instance from brass to strings at a fixed pitch. We demonstrate across three morphing modes: prompt-to-prompt, audio-to-prompt, and audio-to-audio. Evaluations across diverse datasets show that smorph effectively produces smooth morph trajectories while substantially improving temporal-structure and source preservation over baselines, albeit with more conservative target-ward transformation in some settings. In an exploratory case study, musicians found smorph trajectories to be expressive and playable, suggesting structural anchoring can serve as a productive constraint for instrumental interaction.

Problem

• Sound Morphing
• Diffusion Models
• Timbral Identity
• Temporal Structure
• Musical Sound Design

Innovation

• Sound Morphing
• Diffusion Models
• Training-free Guidance
• Timbral Identity
• Temporal Structure