Due to advances in deep learning, the performance of automatic beat and downbeat tracking in musical audio signals has seen great improvement in recent years. In training such deep learning based models, data augmentation has been found an important technique. However, existing data augmentation methods for this task mainly target at balancing the distribution of the training data with respect to their tempo. In this paper, we investigate another approach for data augmentation, to account for the composition of the training data in terms of the percussive and non-percussive sound sources. Specifically, we propose to employ a blind drum separation model to segregate the drum and non-drum sounds from each training audio signal, filtering out training signals that are drumless, and then use the obtained drum and non-drum stems to augment the training data. We report experiments on four completely unseen test sets, validating the effectiveness of the proposed method, and accordingly the importance of drum sound composition in the training data for beat and downbeat tracking.
翻译:由于深层学习的进步,近年来音乐音频信号自动击打和击败跟踪的性能有了很大的改进。在培训这种深层学习模型时,发现数据增强是一项重要技术。然而,目前用于这项任务的数据增强方法主要是平衡培训数据的分布及其节奏。在本文中,我们调查了另一种数据增强方法,以冲击和非冲击音源来说明培训数据的构成情况。具体地说,我们提议使用一个盲鼓分离模型,将鼓和非鼓音从每个培训音频信号中分离开来,过滤无鼓的培训信号,然后使用获得的鼓和非鼓茎来增加培训数据。我们报告四个完全看不见的测试组的实验,以证实拟议方法的有效性,并据此说明鼓声组成在培训数据中对于击打和击落跟踪的重要性。