We address the challenging open problem of learning an effective latent space for symbolic music data in generative music modeling. We focus on leveraging adversarial regularization as a flexible and natural mean to imbue variational autoencoders with context information concerning music genre and style. Through the paper, we show how Gaussian mixtures taking into account music metadata information can be used as an effective prior for the autoencoder latent space, introducing the first Music Adversarial Autoencoder (MusAE). The empirical analysis on a large scale benchmark shows that our model has a higher reconstruction accuracy than state-of-the-art models based on standard variational autoencoders. It is also able to create realistic interpolations between two musical sequences, smoothly changing the dynamics of the different tracks. Experiments show that the model can organise its latent space accordingly to low-level properties of the musical pieces, as well as to embed into the latent variables the high-level genre information injected from the prior distribution to increase its overall performance. This allows us to perform changes to the generated pieces in a principled way.

中文翻译：

---

通过对抗性自动编码器学习风格感知符号音乐表示

我们解决了在生成音乐建模中学习符号音乐数据的有效潜在空间这一具有挑战性的开放问题。我们专注于利用对抗性正则化作为一种​​灵活而自然的手段，为变分自动编码器注入有关音乐流派和风格的上下文信息。通过这篇论文，我们展示了如何将考虑音乐元数据信息的高斯混合用作自动编码器潜在空间的有效先验，介绍了第一个音乐对抗性自动编码器（MusAE）。大规模基准测试的实证分析表明，我们的模型比基于标准变分自动编码器的最新模型具有更高的重建精度。它还能够在两个音乐序列之间创建逼真的插值，平滑地改变不同轨道的动态。实验表明，该模型可以根据音乐作品的低级属性组织其潜在空间，并将从先验分布注入的高级流派信息嵌入到潜在变量中，以提高其整体性能。这使我们能够以一种有原则的方式对生成的片段进行更改。