arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节（Veterans Day），12 日无更新
arXiv 2407.04331cs.SDcs.AIeess.AS
收藏

MuseBarControl：通过预训练与反事实损失增强符号音乐生成中的细粒度控制

MuseBarControl: Enhancing Fine-Grained Control in Symbolic Music Generation through Pre-Training and Counterfactual Loss

School of Computer Science, The University of Adelaide（阿德莱德大学计算机学院）

Yangyang Shu, Haiming Xu, Ziqin Zhou, Anton van den Hengel, Lingqiao Liu

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

MuseBarControl通过设计控制信号与音乐token关联的预训练任务和反事实损失，解决了符号音乐生成中小节级细粒度控制难题，相比传统方法提升13.06%且不损失音乐质量。

摘要：

自动生成符号音乐——即针对特定人类需求定制的乐谱——对音乐家和爱好者可能非常有益。近期研究在使用大规模数据集和先进Transformer架构方面展现了有前景的结果。然而，这些最先进的模型通常只对整个作品提供诸如速度和风格等方面的基本控制，缺乏管理更细粒度细节的能力，例如在单个小节层面进行控制。虽然微调预训练的符号音乐生成模型看似是实现这种更细粒度控制的直接方法，但我们的研究表明这一方法面临挑战：模型往往无法充分响应新的细粒度小节级控制信号。为解决这一问题，我们提出了两种创新方案。首先，我们引入了一项预训练任务，旨在将控制信号直接与相应的音乐token关联起来，这有助于为后续微调实现更有效的初始化。其次，我们实现了一种新颖的反事实损失，以促进生成音乐与控制提示之间更好的对齐。这些技术共同显著增强了我们在小节层面控制音乐生成的能力，相比传统方法提升了13.06%。我们的主观评估也证实，这种增强的控制并未损害原始预训练生成模型的音乐质量。

英文摘要：

Automatically generating symbolic music-music scores tailored to specific human needs-can be highly beneficial for musicians and enthusiasts. Recent studies have shown promising results using extensive datasets and advanced transformer architectures. However, these state-of-the-art models generally offer only basic control over aspects like tempo and style for the entire composition, lacking the ability to manage finer details, such as control at the level of individual bars. While fine-tuning a pre-trained symbolic music generation model might seem like a straightforward method for achieving this finer control, our research indicates challenges in this approach. The model often fails to respond adequately to new, fine-grained bar-level control signals. To address this, we propose two innovative solutions. First, we introduce a pre-training task designed to link control signals directly with corresponding musical tokens, which helps in achieving a more effective initialization for subsequent fine-tuning. Second, we implement a novel counterfactual loss that promotes better alignment between the generated music and the control prompts. Together, these techniques significantly enhance our ability to control music generation at the bar level, showing a 13.06\% improvement over conventional methods. Our subjective evaluations also confirm that this enhanced control does not compromise the musical quality of the original pre-trained generative model.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑