arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.05032cs.SDcs.LGeess.AS
收藏

用于多基频估计及其它任务的软动态时间规整

Soft Dynamic Time Warping for Multi-Pitch Estimation and Beyond

International Audio Laboratories Erlangen(埃尔朗根国际音频实验室);Friedrich-Alexander-Universität Erlangen-Nürnberg(埃尔朗根-纽伦堡弗里德里希-亚历山大大学);Fraunhofer Institute for Integrated Circuits IIS(弗劳恩霍夫集成电路研究所IIS)

Michael Krause, Christof Weiß, Meinard Müller

AI总结:

本文提出用可微的软动态时间规整(SoftDTW)替代CTC处理弱对齐数据,在多基频估计上达到与最先进CTC多标签扩展相当的性能,并支持实值目标序列。

摘要:

音乐信息检索(MIR)中的许多任务涉及弱对齐数据,其中精确的时间对应关系未知。连接主义时序分类(CTC)损失是基于弱对齐训练数据学习特征表示的标准技术。然而,CTC仅限于离散值目标序列,并且难以扩展到多标签问题。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,我们表明SoftDTW取得了与最先进的CTC多标签扩展相当的结果。除了在算法表述上更为优雅之外,SoftDTW还自然地扩展到实值目标序列。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑