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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Haowen, Li, Tianxiang, Yang, Yi, Cao, Boyu, Liu, Qi
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910207911657472
author Li, Haowen
Li, Tianxiang
Yang, Yi
Cao, Boyu
Liu, Qi
author_facet Li, Haowen
Li, Tianxiang
Yang, Yi
Cao, Boyu
Liu, Qi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_10203
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Polyphonia: Zero-Shot Timbre Transfer in Polyphonic Music with Acoustic-Informed Attention Calibration
Li, Haowen
Li, Tianxiang
Yang, Yi
Cao, Boyu
Liu, Qi
Sound
Audio and Speech Processing
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.
title Polyphonia: Zero-Shot Timbre Transfer in Polyphonic Music with Acoustic-Informed Attention Calibration
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2605.10203