Subjective Melodic Similarity based on Extended Implication-Realization Model
Subjective Melodic Similarity based on Extended Implication-Realization Model
复制标题
基于扩展含义实现模型的主观旋律相似度
DOI：
10.5057/ijae.ijae-d-15-00050
复制
发表时间：
2016
影响因子：
0.3
通讯作者：
T. Utsuro
中科院分区：
文献类型：
--
作者：
Sakurako Yazawa;Masatoshi Hamanaka;T. Utsuro
本文提出了如何基于蕴涵实现模型（IRM）来衡量旋律的相似度。 IRM是一种音乐理论，其基础是对音乐进行抽象，然后通过符号序列来表达音乐，符号序列是构成音乐的信息，如音高、节奏、休止符等。本文特别扩展了IRM，使该理论更加适合测量旋律的相似度。更具体地说，与原始IRM的符号相比，我们通过简单区分区间方向的上下并将原始IRM的每个大多数符号划分为两个扩展符号来引入更细粒度的符号。此外，我们实现了一个解析器，将输入旋律的音符序列转换为扩展 IRM 符号的序列。通过人类主观判断进行的实验评估结果表明，在测量旋律相似性方面，所提出的扩展 IRM 符号优于原始 IRM 符号。
This paper proposes how to measure similarity of melodies based on Implication-Realization Model (IRM). IRM is a music theory based on abstracting music and then expressing music through symbol sequences which is information constituting the music such as pitch, rhythm, and rests and so on. This paper especially extends IRM so that the theory becomes much more appropriate to measuring similarity of melodies. More specifically, compared with the symbols of the original IRM, we introduce finer grained symbols by simply distinguishing up and down of interval directions and by dividing each most symbols of the original IRM into two extended symbols. Furthermore, we implement a parser that transforms note sequence of an input melody into a sequence of the extended IRM symbols. The results of experimental evaluation through subjective human judgments show that the proposed extended IRM symbols outperform the original IRM symbols with respect to measuring similarity of melodies.