We propose a new graph convolutional block, called MusGConv, specifically
designed for the efficient processing of musical score data and motivated by
general perceptual principles. It focuses on two fundamental dimensions of
music, pitch and rhythm, and considers both relative and absolute
representations of these components. We evaluate our approach on four different
musical understanding problems: monophonic voice separation, harmonic analysis,
cadence detection, and composer identification which, in abstract terms,
translate to different graph learning problems, namely, node classification,
link prediction, and graph classification. Our experiments demonstrate that
MusGConv improves the performance on three of the aforementioned tasks while
being conceptually very simple and efficient. We interpret this as evidence
that it is beneficial to include perception-informed processing of fundamental
musical concepts when developing graph network applications on musical score
data.

我们提出了一种新的图卷积块，称为 MusGConv，专门为高效处理音乐乐谱数据而设计，并根据一般感知原理进行了激发。它关注音乐的两个基本维度，音高和节奏，并考虑了这些组成部分的相对和绝对表示。我们在四个不同的音乐理解问题上评估了我们的方法：单声部分离、和声分析、乐句检测和作曲家识别，这在抽象术语中转化为不同的图学习问题，即节点分类、链接预测和图分类。我们的实验证明了 MusGConv 在以上三个任务上改善了性能，同时概念上非常简单和高效。我们解释这一结果是证据表明，在开发音乐乐谱数据的图网络应用时，包括基本音乐概念的感知驱动处理是有益的。

感知启发的图卷积在音乐理解任务中的应用

Perception-Inspired Graph Convolution for Music Understanding Tasks

We use Google's MusicVAE, a Variational Auto-Encoder with a 512-dimensional
latent space to represent a few bars of music, and organize the latent
dimensions according to their relevance in describing music. We find that, on
average, most latent neurons remain silent when fed real music tracks: we call
these "noise" neurons. The remaining few dozens of latent neurons that do fire
are called "music neurons". We ask which neurons carry the musical information
and what kind of musical information they encode, namely something that can be
identified as pitch, rhythm or melody. We find that most of the information
about pitch and rhythm is encoded in the first few music neurons: the neural
network has thus constructed a couple of variables that non-linearly encode
many human-defined variables used to describe pitch and rhythm. The concept of
melody only seems to show up in independent neurons for longer sequences of
music.

我们使用 Google 的 MusicVAE，一个具有 512 维潜在空间的变分自动编码器来表示几小节的音乐，并根据描述音乐的相关性组织潜在维度。我们发现，平均而言，大多数潜在神经元在输入真实音乐曲目时保持沉默：我们称这些为 “噪声” 神经元。剩下的几十个激活的潜在神经元被称为 “音乐” 神经元。我们探究哪些神经元携带音乐信息以及它们编码的音乐信息种类，即是否可以识别为音高、节奏或旋律。我们发现大部分关于音高和节奏的信息都编码在最开始的几个音乐神经元中：神经网络因此构建了一些非线性编码许多用于描述音高和节奏的人工定义变量的变量。旋律的概念似乎仅在较长的音乐序列中出现独立的神经元中。