Music representation learning is notoriously difficult for its complex
human-related concepts contained in the sequence of numerical signals. To
excavate better MUsic SEquence Representation from labeled audio, we propose a
novel text-supervision pre-training method, namely MUSER. MUSER adopts an
audio-spectrum-text tri-modal contrastive learning framework, where the text
input could be any form of meta-data with the help of text templates while the
spectrum is derived from an audio sequence. Our experiments reveal that MUSER
could be more flexibly adapted to downstream tasks compared with the current
data-hungry pre-training method, and it only requires 0.056% of pre-training
data to achieve the state-of-the-art performance.

本文提出了一种新的文本监督预训练方法 MUSER，采用音频 - 频谱 - 文本三模态对比学习框架，通过任何形式的元数据模板来帮助文本输入，从标记音频中挖掘更好的音乐序列表示，具有比当前数据密集型预训练方法更灵活地适应下游任务以及只需要 0.056％的预训练数据就能达到最先进性能的优势。

从文本监督中学习音乐序列表示

Learning Music Sequence Representation from Text Supervision

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。