The dominant approach for music representation learning involves the deep
unsupervised model family variational autoencoder (VAE). However, most, if not
all, viable attempts on this problem have largely been limited to monophonic
music. Normally composed of richer modality and more complex musical
structures, the polyphonic counterpart has yet to be addressed in the context
of music representation learning. In this work, we propose the PianoTree VAE, a
novel tree-structure extension upon VAE aiming to fit the polyphonic music
learning. The experiments prove the validity of the PianoTree VAE via
(i)-semantically meaningful latent code for polyphonic segments; (ii)-more
satisfiable reconstruction aside of decent geometry learned in the latent
space; (iii)-this model's benefits to the variety of the downstream music
generation.

本文提出了一种名为 PianoTree VAE 的新型树结构扩展 VAE 用于拟合多声部音乐学习，并通过实验验证了其（一）适用于多声部片段的语义有意义的潜在编码；（二）除了可接受的几何形状学习外，更具有令人满意的重构性能；（三）对下游音乐生成的多样性有益。