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 2203.15468cs.SDcs.LGeess.AS
收藏

基于拓扑数据分析和人工神经网络的朝鲜音乐机器合成

Machine Composition of Korean Music via Topological Data Analysis and Artificial Neural Network

Pohang University of Science & Technology(浦项科技大学)

Mai Lan Tran, Dongjin Lee, Jae-Hun Jung

摘要:

常见的基于人工神经网络的人工智能音乐作曲算法是通过输入大量音乐片段来训练机器,并创建能够产生与输入音乐数据相似的音乐的人工神经网络。这种方法是一种黑盒优化,也就是说,底层的合成算法通常不为用户所知。在本文中,我们提出了一种机器作曲的方式,训练机器的作曲原理嵌入在给定的音乐数据,而不是直接喂养的音乐作品。我们提出这种方法,通过使用的概念,{ \color{black}{Overlap} }矩阵提出的\cite{TPJ}。在\cite{TPJ}中,使用拓扑数据分析(TDA),特别是使用持久同源性,分析了一种类型的韩国音乐,所谓的{ \it Dodeuri}音乐,例如Suyeonjangjigok。由于原始音乐数据不适合于TDA分析,因此首先将音乐数据重构为图。图的节点被定义为由每个音符的音高和持续时间组成的二维向量。当两个节点连续出现在音乐流中时,会创建这些节点之间的边。距离是根据这种出现的频率来定义的。通过TDA的构造图,一个唯一的一组周期被发现为给定的音乐。在\cite{TPJ}中,已经提出了{ \it { \color{black}{Overlap} }矩阵}的新概念,其以矩阵形式可视化这些循环如何在音乐流上互连。在本文中,我们解释了如何使用{ \color{black}{Overlap} }矩阵的机器组成。{ \color{black}{Overlap} }矩阵使得有可能在算法上组成新的音乐作品,并且还向期望的人工神经网络提供种子音乐。在本文中,我们使用{ \it Dodeuri}音乐,并解释详细的步骤。

英文摘要:

Common AI music composition algorithms based on artificial neural networks are to train a machine by feeding a large number of music pieces and create artificial neural networks that can produce music similar to the input music data. This approach is a blackbox optimization, that is, the underlying composition algorithm is, in general, not known to users. In this paper, we present a way of machine composition that trains a machine the composition principle embedded in the given music data instead of directly feeding music pieces. We propose this approach by using the concept of {\color{black}{Overlap}} matrix proposed in \cite{TPJ}. In \cite{TPJ}, a type of Korean music, so-called the {\it Dodeuri} music such as Suyeonjangjigok has been analyzed using topological data analysis (TDA), particularly using persistent homology. As the raw music data is not suitable for TDA analysis, the music data is first reconstructed as a graph. The node of the graph is defined as a two-dimensional vector composed of the pitch and duration of each music note. The edge between two nodes is created when those nodes appear consecutively in the music flow. Distance is defined based on the frequency of such appearances. Through TDA on the constructed graph, a unique set of cycles is found for the given music. In \cite{TPJ}, the new concept of the {\it {\color{black}{Overlap}} matrix} has been proposed, which visualizes how those cycles are interconnected over the music flow, in a matrix form. In this paper, we explain how we use the {\color{black}{Overlap}} matrix for machine composition. The {\color{black}{Overlap}} matrix makes it possible to compose a new music piece algorithmically and also provide a seed music towards the desired artificial neural network. In this paper, we use the {\it Dodeuri} music and explain detailed steps.

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。

↑