论文标题
SSM-NET：使用基于自相似的损失的音乐结构分析的功能学习。
SSM-Net: feature learning for Music Structure Analysis using a Self-Similarity-Matrix based loss
论文作者
论文摘要
在本文中，我们提出了一个新的范式来学习音乐结构分析（MSA）的音频功能。我们训练一个深层编码器来学习特征，从而使这些特征是由近似于地面的SSM产生的自相似性矩阵（SSM）。这是通过最大程度地减少两个SSM之间的损失来完成的。由于这种损失是可区分的W.R.T.它的输入功能我们可以直接地训练编码器。我们成功地证明了使用RWC-POP数据集上曲线ROC（AUC）下的区域下的训练范式的使用。
In this paper, we propose a new paradigm to learn audio features for Music Structure Analysis (MSA). We train a deep encoder to learn features such that the Self-Similarity-Matrix (SSM) resulting from those approximates a ground-truth SSM. This is done by minimizing a loss between both SSMs. Since this loss is differentiable w.r.t. its input features we can train the encoder in a straightforward way. We successfully demonstrate the use of this training paradigm using the Area Under the Curve ROC (AUC) on the RWC-Pop dataset.
