Many tasks in music information retrieval (MIR) involve weakly aligned data, where exact temporal correspondences are unknown. The connectionist temporal classification (CTC) loss is a standard technique to learn feature representations based on weakly aligned training data. However, CTC is limited to discrete-valued target sequences and can be difficult to extend to multi-label problems. In this article, we show how soft dynamic time warping (SoftDTW), a differentiable variant of classical DTW, can be used as an alternative to CTC. Using multi-pitch estimation as an example scenario, we show that SoftDTW yields results on par with a state-of-the-art multi-label extension of CTC. In addition to being more elegant in terms of its algorithmic formulation, SoftDTW naturally extends to real-valued target sequences.

翻译：音乐信息检索（MIR）中的许多任务涉及弱对齐数据，即精确的时间对应关系未知。连接主义时序分类（CTC）损失是一种基于弱对齐训练数据学习特征表示的标准技术。然而，CTC仅限于离散值的目标序列，且难以扩展至多标签问题。在本文中，我们展示了软动态时间规整（SoftDTW）——经典DTW的一种可微变体——如何作为CTC的替代方案。以多基频估计为例，我们证明SoftDTW能够获得与最先进的多标签CTC扩展方法相当的结果。除了在算法表述上更为简洁之外，SoftDTW自然适用于实数值目标序列。