论文标题
DMELODIES：一个用于解剖学学习的音乐数据集
dMelodies: A Music Dataset for Disentanglement Learning
论文作者
论文摘要
代表学习的重点是解散给定数据中的差异因素已成为机器学习研究的重要领域。但是，该领域的大多数研究都依赖于计算机视觉域中的数据集，因此并未容易扩展到音乐。在本文中，我们提出了一个新的符号音乐数据集，该数据集将帮助研究分解问题的研究人员证明其算法对不同领域的功效。这还将提供一种评估专门为音乐设计的算法的方法。为此，我们创建了一个包含2杆单声音旋律的数据集，其中每个旋律都是跨越序数，分类和二进制类型的九种潜在因素的独特组合的结果。该数据集足够大（大约130万个数据点），可以训练和测试深层网络以进行分离学习。此外，我们使用该数据集中流行的无监督分解算法提出了基准测试实验，并将结果与基于图像的数据集获得的结果进行比较。
Representation learning focused on disentangling the underlying factors of variation in given data has become an important area of research in machine learning. However, most of the studies in this area have relied on datasets from the computer vision domain and thus, have not been readily extended to music. In this paper, we present a new symbolic music dataset that will help researchers working on disentanglement problems demonstrate the efficacy of their algorithms on diverse domains. This will also provide a means for evaluating algorithms specifically designed for music. To this end, we create a dataset comprising of 2-bar monophonic melodies where each melody is the result of a unique combination of nine latent factors that span ordinal, categorical, and binary types. The dataset is large enough (approx. 1.3 million data points) to train and test deep networks for disentanglement learning. In addition, we present benchmarking experiments using popular unsupervised disentanglement algorithms on this dataset and compare the results with those obtained on an image-based dataset.
