为什么扰动符号音乐是必要的：通过联合概率扩散模型拟合从未使用音符的分布
Why Perturbing Symbolic Music is Necessary: Fitting the Distribution of Never-used Notes through a Joint Probabilistic Diffusion Model
AI总结：
针对语言式音乐生成模型难以拟合稀有音符的问题，提出 Music-Diff 联合概率扩散架构，通过语义分片、联合预训练与 Pareto 多分支去噪提升符号音乐的多样性和结构规则性。
摘要：
现有的音乐生成模型大多基于语言，忽视了音符的频率连续性属性，导致对稀有或从未使用音符的拟合不足，进而降低了生成样本的多样性。我们认为，音符分布可以通过平移不变性和周期性来建模，尤其是利用扩散模型通过注入频域高斯噪声来泛化音符。然而，由于音乐符号的低密度特性，估计潜藏在高密度解空间中的音符分布带来了重大挑战。为解决这一问题，我们提出 Music-Diff 架构，该架构拟合音符与伴随语义信息的联合分布，以有条件地生成符号音乐。我们首先使用基于事件的记谱法和结构相似性指数增强用于提取语义的分片模块，从而防止边界模糊。作为多变量扰动的先决条件，我们引入一种联合预训练方法，以构建音符与音乐语义之间的进行关系，同时避免直接建模低密度音符。最后，我们通过多分支去噪器恢复受扰动的音符，该去噪器通过 Pareto 优化拟合多个噪声目标。实验表明，与语言模型相比，在音符和语义两个层面进行扰动的联合概率扩散模型能够提供更高的样本多样性和作曲规则性。案例研究通过分析自相似性指标所表达的层级结构，突显了本模型相对于基于语言模型和基于 DDPM 的模型在节奏方面的优势。
英文摘要：
Existing music generation models are mostly language-based, neglecting the frequency continuity property of notes, resulting in inadequate fitting of rare or never-used notes and thus reducing the diversity of generated samples. We argue that the distribution of notes can be modeled by translational invariance and periodicity, especially using diffusion models to generalize notes by injecting frequency-domain Gaussian noise. However, due to the low-density nature of music symbols, estimating the distribution of notes latent in the high-density solution space poses significant challenges. To address this problem, we introduce the Music-Diff architecture, which fits a joint distribution of notes and accompanying semantic information to generate symbolic music conditionally. We first enhance the fragmentation module for extracting semantics by using event-based notations and the structural similarity index, thereby preventing boundary blurring. As a prerequisite for multivariate perturbation, we introduce a joint pre-training method to construct the progressions between notes and musical semantics while avoiding direct modeling of low-density notes. Finally, we recover the perturbed notes by a multi-branch denoiser that fits multiple noise objectives via Pareto optimization. Our experiments suggest that in contrast to language models, joint probability diffusion models perturbing at both note and semantic levels can provide more sample diversity and compositional regularity. The case study highlights the rhythmic advantages of our model over language- and DDPMs-based models by analyzing the hierarchical structure expressed in the self-similarity metrics.
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。
