FlowSonic：通过高阶轨迹积分实现稳定的零样本音乐编辑
FlowSonic: Stable Zero-Shot Music Editing via High-Order Trajectory Integration
浏览论文内容
中文总结 AI 辅助
研究针对真实音乐录音零样本编辑难题，提出FlowSonic框架，基于预训练扩散变压器，通过重用交叉注意力表示保留结构，引入高阶ODE求解器，实验表明其在多方面优于现有方法，能提高潜在轨迹稳定性实现可靠编辑。
中文摘要 AI 辅助
对真实世界音乐录音进行零样本文本引导编辑，需要在语义修改与忠实保留原始音乐结构之间取得平衡。尽管最近基于整流流训练的扩散变压器在文本到音乐生成方面取得了显著成功，但将其扩展到编辑现有录音仍具有挑战性。我们提出了FlowSonic，一个基于预训练的整流流扩散变压器的零样本音乐编辑框架。它先将真实录音确定性地逆变换到潜在空间，并在编辑时通过重用逆变换过程中提取的交叉注意力表示来保留音乐结构。为提高基于逆变换编辑的数值可靠性，引入高阶常微分方程求解器并研究不同数值积分方案对轨迹稳定性、结构保留和语义可控性的影响。在音色转换和风格修改任务上的综合实验表明，FlowSonic在语义对齐、和声保留、结构一致性和感知音频质量方面始终优于现有音乐编辑方法。我们还提供了几何和实证分析，展示了所提出的数值积分策略如何提高潜在轨迹稳定性并实现更可靠的音乐编辑。
英文摘要
Zero-shot text-guided editing of real-world music recordings requires balancing semantic modification with faithful preservation of the original musical structure. Although recent diffusion transformers trained with rectified flow have achieved remarkable success in text-to-music generation, extending them to edit existing recordings remains challenging because editing requires accurate deterministic inversion, reliable structural preservation, and numerically stable integration throughout the inversion and generation processes. We present FlowSonic, a zero-shot music editing framework built upon a pretrained diffusion transformer trained with rectified flow. FlowSonic first deterministically inverts a real-world recording into the latent space and preserves its musical structure during editing by reusing cross-attention representations extracted during inversion. To improve the numerical reliability of inversion-based editing, we introduce a high-order ODE solver and systematically investigate how different numerical integration schemes influence trajectory stability, structural preservation, and semantic controllability. Comprehensive experiments on timbre-transfer and genre-modification tasks demonstrate that FlowSonic consistently outperforms existing music editing methods across semantic alignment, harmonic preservation, structural consistency, and perceptual audio quality. We further provide geometric and empirical analyses showing how the proposed numerical integration strategy improves latent trajectory stability and leads to more reliable music editing.
