Part-invariant Model for Music Generation and Harmonization
Part-invariant Model for Music Generation and Harmonization
复制标题
音乐生成和和声的部分不变模型
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Z. Duan
中科院分区：
文献类型：
--
作者：
Yujia Yan;Ethan Lustig;Joseph VanderStel;Z. Duan
近年来，自动音乐生成越来越受到关注。然而，现有的方法大多是针对特定的节奏结构或乐器布局，并且在评估中缺乏音乐理论的严谨性。在本文中，我们提出了一种神经语言（音乐）模型，试图对符号多部分音乐进行建模。我们的模型是部分不变的，即它可以使用单个训练模型处理/生成由任意数量的部分组成的乐谱的任何部分（声音）。为了更好地合并音调空间的结构信息，我们使用结构化嵌入矩阵将音调的多个方面编码为向量表示。该生成由吉布斯采样执行。同时，我们的模型直接生成注释拼写，使输出易于人类阅读。我们通过招募音乐理论家来将我们的算法的输出与音乐学生在低音线协调任务（传统的教学任务）上的输出进行比较，从而进行客观（评分）和主观（听力）评估。我们的实验表明，我们的算法和学生的错误分布不同，并且对于我们提供的三个低音线，生成的作品的评分范围与学生的评分范围有不同程度的重叠。这个实验提出了一些未来的研究方向。
Automatic music generation has been gaining more attention in recent years. Existing approaches, however, are mostly ad hoc to specific rhythmic structures or instrumentation layouts, and lack music-theoretic rigor in their evaluations. In this paper, we present a neural language (music) model that tries to model symbolic multi-part music. Our model is part-invariant, i.e., it can process/generate any part (voice) of a music score consisting of an arbitrary number of parts, using a single trained model. For better incorporating structural information of pitch spaces, we use a structured embedding matrix to encode multiple aspects of a pitch into a vector representation. The generation is performed by Gibbs Sampling. Meanwhile, our model directly generates note spellings to make outputs human-readable. We performed objective (grading) and subjective (listening) evaluations by recruiting music the-orists to compare the outputs of our algorithm with those of music students on the task of bassline harmonization (a traditional pedagogical task). Our experiment shows that errors of our algorithm and students are differently distributed, and the range of ratings for generated pieces overlaps with students’ to varying extents for our three provided basslines. This experiment suggests some future research directions.
DOI：
--
发表时间：
2019-03
期刊：
--
影响因子：
--
作者：
Cheng-Zhi Anna Huang;Tim Cooijmans;Adam Roberts;Aaron C. Courville;D. Eck
通讯作者：
Cheng-Zhi Anna Huang;Tim Cooijmans;Adam Roberts;Aaron C. Courville;D. Eck