audioLIME: Listenable Explanations Using Source Separation

Abstract

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.

In The 13th International Workshop on Machine Learning and Music, ECML-PKDD 2020

References in corpus (2)

• Sample-level Deep Convolutional Neural Networks for Music Auto-tagging Using Raw Waveforms
• Evaluation of CNN-based Automatic Music Tagging Models

Cited by in corpus (5)

• Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges
• What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structure
• Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualities
• On the Veracity of Local, Model-agnostic Explanations in Audio Classification: Targeted Investigations with Adversarial Examples
• Towards Interpretable ANNs: An Exact Transformation to Multi-Class Multivariate Decision Trees