Reliable Local Explanations for Machine Listening

TL;DR

This paper investigates how to generate reliable local explanations for machine listening models, focusing on sensitivity to input perturbations and proposing a method to identify suitable content types for occlusion, demonstrated on a singing voice detection model.

Contribution

It introduces a novel method to identify appropriate content types for input occlusion, enhancing the reliability of local explanations in machine listening models.

Findings

SoundLIME explanations are sensitive to input content.

Average magnitude of mel-spectrogram bins is effective for occlusion.

Proposed method improves explanation reliability.

Abstract

One way to analyse the behaviour of machine learning models is through local explanations that highlight input features that maximally influence model predictions. Sensitivity analysis, which involves analysing the effect of input perturbations on model predictions, is one of the methods to generate local explanations. Meaningful input perturbations are essential for generating reliable explanations, but there exists limited work on what such perturbations are and how to perform them. This work investigates these questions in the context of machine listening models that analyse audio. Specifically, we use a state-of-the-art deep singing voice detection (SVD) model to analyse whether explanations from SoundLIME (a local explanation method) are sensitive to how the method perturbs model inputs. The results demonstrate that SoundLIME explanations are sensitive to the content in the occluded input regions. We further propose and demonstrate a novel method for quantitatively identifying suitable content type(s) for reliably occluding inputs of machine listening models. The results for the SVD model suggest that the average magnitude of input mel-spectrogram bins is the most suitable content type for temporal explanations.