无需重训，通过潜空间调节实现作曲家风格的灵活控制
Composer Vector: Style-steering Symbolic Music Generation in a Latent Space
- 在模型潜空间中引入作曲家向量，实现推理时风格调节
- 支持多风格平滑融合，单次生成可混合多种作曲家风格
- 无需标注数据，适用于各类符号音乐生成模型
符号化音乐生成已取得显著进展，但对作曲家风格进行细粒度且灵活的控制仍具挑战。现有基于训练的方法依赖大规模带标签数据，且通常只能单次生成单一作曲家风格，限制了其在更富创意或混合风格场景中的应用。本文提出Composer Vector，一种在推理阶段直接作用于模型潜空间的风格调节方法，无需重训即可控制作曲家风格。在多个符号音乐生成模型上的实验表明，Composer Vector能有效引导生成结果向目标作曲家风格靠拢，通过连续调节系数实现平滑、可解释的风格控制，并可在统一潜空间框架内无缝融合多种风格。结果证明，简单的潜空间调节提供了一种实用且通用的可控符号音乐生成机制，支持更灵活、交互式创作流程。代码与演示见：https://github.com/JiangXunyi/Composer-Vector 及 https://jiangxunyi.github.io/composervector.github.io/
原文摘要 · Abstract (English)
Symbolic music generation has made significant progress, yet achieving fine-grained and flexible control over composer style remains challenging. Existing training-based methods for composer style conditioning depend on large labeled datasets. Besides, these methods typically support only single-composer generation at a time, limiting their applicability to more creative or blended scenarios. In this work, we propose Composer Vector, an inference-time steering method that operates directly in the model's latent space to control composer style without retraining. Through experiments on multiple symbolic music generation models, we show that Composer Vector effectively guides generations toward target composer styles, enabling smooth and interpretable control through a continuous steering coefficient. It also enables seamless fusion of multiple styles within a unified latent space framework. Overall, our work demonstrates that simple latent space steering provides a practical and general mechanism for controllable symbolic music generation, enabling more flexible and interactive creative workflows. Code and Demo are available here: https://github.com/JiangXunyi/Composer-Vector and https://jiangxunyi.github.io/composervector.github.io/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。