Ambisonics is a scene-based spatial audio format that has several useful features compared to object-based formats, such as efficient whole scene rotation and versatility. However, it does not provide direct access to the individual source signals, so that these have to be separated from the mixture when required. Typically, this is done with linear spherical harmonics (SH) beamforming. In this paper, we explore deep-learning-based source separation on static Ambisonics mixtures. In contrast to most source separation approaches, which separate a fixed number of sources of specific sound types, we focus on separating arbitrary sound from specific directions. Specifically, we propose three operating modes that combine a source separation neural network with SH beamforming: refinement, implicit, and mixed mode. We show that a neural network can implicitly associate conditioning directions with the spatial information contained in the Ambisonics scene to extract specific sources. We evaluate the performance of the three proposed approaches and compare them to SH beamforming on musical mixtures generated with the musdb18 dataset, as well as with mixtures generated with the FUSS dataset for universal source separation, under both anechoic and room conditions. Results show that the proposed approaches offer improved separation performance and spatial selectivity compared to conventional SH beamforming.

翻译：Ambisonics是一种基于场景的空间音频格式，相较于基于对象的格式具有若干实用特性，例如高效的全场景旋转和多功能性。然而，它无法直接访问单个源信号，因此需要在需要时从混合信号中分离出这些信号。通常，这通过线性球谐波束形成来实现。本文探索了基于深度学习的静态Ambisonics混合信号源分离方法。与大多数针对特定声音类型固定数量源进行分离的方法不同，我们专注于从特定方向分离任意声音。具体而言，我们提出了三种操作模式，将源分离神经网络与球谐波束形成相结合：细化模式、隐式模式和混合模式。研究表明，神经网络能够隐式地将条件方向与Ambisonics场景中包含的空间信息关联起来，从而提取特定源信号。我们评估了三种所提出方法的性能，并在消声和室内条件下，将其与基于musdb18数据集生成的音乐混合信号以及基于通用源分离FUSS数据集生成的混合信号上的球谐波束形成方法进行了比较。结果表明，与传统球谐波束形成相比，所提出的方法在分离性能和空间选择性方面均有提升。