# Reliable Local Explanations for Machine Listening

arXiv: https://arxiv.org/abs/2005.07788 · HTML: https://mlsanity.com/paper/2005.07788/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 May 2020.

## Built on by (most cited first, 18 of 18)

- [A Survey on the Robustness of Feature Importance and Counterfactual Explanations](https://mlsanity.com/paper/2111.00358/) (2021)
- [Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF](https://mlsanity.com/paper/2202.11479/) (2022)
- [Listenable Maps for Audio Classifiers](https://mlsanity.com/paper/2403.13086/) (2024)
- [Concept-Based Techniques for "Musicologist-friendly" Explanations in a Deep Music Classifier](https://mlsanity.com/paper/2208.12485/) (2022)
- [Tracing Back Music Emotion Predictions to Sound Sources and Intuitive Perceptual Qualities](https://mlsanity.com/paper/2106.07787/) (2021)
- [Time is Not Enough: Time-Frequency based Explanation for Time-Series Black-Box Models](https://mlsanity.com/paper/2408.03636/) (2024)
- [Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorization](https://mlsanity.com/paper/2305.07132/) (2023)
- [Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speech](https://mlsanity.com/paper/2411.08013/) (2024)
- [On the Veracity of Local, Model-agnostic Explanations in Audio Classification: Targeted Investigations with Adversarial Examples](https://mlsanity.com/paper/2107.09045/) (2021)
- [Listenable Maps for Zero-Shot Audio Classifiers](https://mlsanity.com/paper/2405.17615/) (2024)
- [One Wave To Explain Them All: A Unifying Perspective On Feature Attribution](https://mlsanity.com/paper/2410.01482/) (2024)
- [Investigating Modality Contribution in Audio LLMs for Music](https://mlsanity.com/paper/2509.20641/) (2025)
- [Explainable Deep Learning Framework for Human Activity Recognition](https://mlsanity.com/paper/2408.11552/) (2024)
- [Prevailing Research Areas for Music AI in the Era of Foundation Models](https://mlsanity.com/paper/2409.09378/) (2024)
- ["I made this (sort of)": Negotiating authorship, confronting fraudulence, and exploring new musical spaces with prompt-based AI music generation](https://mlsanity.com/paper/2507.23365/) (2025)
- [Mask-Induced Displacement in Audio XAI via Logit Trajectory Decomposition](https://mlsanity.com/paper/2609.33486/) (2026)
- [Uncovering shortcut learning in audio classifiers by discovering recurring concepts in temporal explanations](https://mlsanity.com/paper/2609.34030/) (2026)
- [Faithfulness Without Anchors: A Position Paper on the Structural Misalignments of Explainable AI Faithfulness Metrics for Feature Importance](https://mlsanity.com/paper/2610.12493/) (2026)

## Abstract (arXiv)

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.