论文标题
Audiolime：使用源分离的可听解释
audioLIME: Listenable Explanations Using Source Separation
论文作者
论文摘要
深层神经网络（DNN）成功地应用于各种音乐信息检索（MIR）任务中，但它们的预测通常不可解释。我们提出了Audiolime，这是一种基于局部可解释的模型敏捷解释（LIME）的方法，该解释是通过当地的音乐定义扩展的。石灰中使用的扰动是通过通过源分离提取的开/关组件来创建的，这使我们的解释可听。我们在两个不同的音乐标记系统上验证了Audiolime，并表明它在竞争方法无法进行的情况下产生明智的解释。
Deep neural networks (DNNs) are successfully applied in a wide variety of music information retrieval (MIR) tasks but their predictions are usually not interpretable. We propose audioLIME, a method based on Local Interpretable Model-agnostic Explanations (LIME) extended by a musical definition of locality. The perturbations used in LIME are created by switching on/off components extracted by source separation which makes our explanations listenable. We validate audioLIME on two different music tagging systems and show that it produces sensible explanations in situations where a competing method cannot.
