Polyphonia: Zero-Shot Timbre Transfer in Polyphonic Music with Acoustic-Informed Attention Calibration

TL;DR

Polyphonia introduces a zero-shot timbre transfer method for polyphonic music that uses acoustic-informed attention calibration to improve stem-specific editing accuracy.

Contribution

It presents a novel framework combining semantic attention with acoustic priors for precise stem-specific timbre transfer in dense musical mixtures.

Findings

Achieves 15.5% higher target alignment than baselines.

Maintains competitive music fidelity.

Effectively localizes targets with reduced boundary leakage.

Abstract

The advancement of diffusion-based text-to-music generation has opened new avenues for zero-shot music editing. However, existing methods fail to achieve stem-specific timbre transfer, which requires altering specific stems while strictly preserving the background accompaniment. This limitation severely hinders practical application, since real-world production necessitates precise manipulation of components within dense mixtures. Our key finding is that, while vanilla cross-attention captures semantic features of stems, it lacks the spectral resolution to strictly localize targets in dense mixtures, leading to boundary leakage. To resolve this dilemma, we propose Polyphonia, a zero-shot editing framework with Acoustic-Informed Attention Calibration. Rather than relying solely on diffuse semantic attention, Polyphonia leverages a probabilistic acoustic prior to establish coarse boundaries, enabling non-target stems preserved precise semantic synthesis. For evaluation, we propose PolyEvalPrompts, a standardized prompt set with 1,170 timbre transfer tasks in polyphonic music. Specifically, Polyphonia achieves an increase of 15.5% in target alignment compared to baselines, while maintaining competitive music fidelity and non-target integrity.