End-to-end generation of musical audio using deep learning techniques has
seen an explosion of activity recently. However, most models concentrate on
generating fully mixed music in response to abstract conditioning information.
In this work, we present an alternative paradigm for producing music generation
models that can listen and respond to musical context. We describe how such a
model can be constructed using a non-autoregressive, transformer-based model
architecture and present a number of novel architectural and sampling
improvements. We train the described architecture on both an open-source and a
proprietary dataset. We evaluate the produced models using standard quality
metrics and a new approach based on music information retrieval descriptors.
The resulting model reaches the audio quality of state-of-the-art
text-conditioned models, as well as exhibiting strong musical coherence with
its context.

使用深度学习技术的音乐音频的端到端生成最近有很大活动。本文提出了一种替代范式，用于生成能够听取和响应音乐上下文的音乐生成模型。使用非自回归、基于 Transformer 的模型架构构建了这样一个模型，并提出了一系列新颖的架构和采样改进方法。我们在开源和专有数据集上训练了这个描述的架构。我们使用标准质量度量和基于音乐信息检索描述符的新方法来评估生成的模型。所得到的模型在音频质量上达到了最先进的基于文本的模型水平，并且在音乐连贯性方面表现出很强的上下文关联性。