Audiomnist: Exploring Explainable Artificial Intelligence For Audio Analysis On A Simple Benchmark

Abstract

Explainable Artificial Intelligence (XAI) is targeted at understanding how models perform feature selection and derive their classification decisions. This paper explores post-hoc explanations for deep neural networks in the audio domain. Notably, we present a novel Open Source audio dataset consisting of 30,000 audio samples of English spoken digits which we use for classification tasks on spoken digits and speakers' biological sex. We use the popular XAI technique Layer-wise Relevance Propagation (LRP) to identify relevant features for two neural network architectures that process either waveform or spectrogram representations of the data. Based on the relevance scores obtained from LRP, hypotheses about the neural networks' feature selection are derived and subsequently tested through systematic manipulations of the input data. Further, we take a step beyond visual explanations and introduce audible heatmaps. We demonstrate the superior interpretability of audible explanations over

Stats

• citations62
• S2 citations—
• github stars0
• HF likes0
• heat score13.50
• arxiv keybecker2018audiomnist

Related papers

• Explainable AI In Speaker Recognition -- Making Latent Representations Understandable (2026)0.00
• Interpreting End-to-end Deep Learning Models For Speech Source Localization Using Layer-wise Relevance Propagation (2024)2.26
• Explainable By-design Audio Segmentation Through Non-negative Matrix Factorization And Probing (2024)3.58
• All That Glitters Is Not Audio: Rethinking Text Priors And Audio Reliance In Audio-language Evaluation (2026)0.00
• Visualizing Automatic Speech Recognition -- Means For A Better Understanding? (2022)4.52
• Step-audio-r1.5 Technical Report (2026)0.00
• Perceptual Musical Features For Interpretable Audio Tagging (2023)5.24
• Measuring Audio's Impact On Correctness: Audio-contribution-aware Post-training Of Large Audio Language Models (2025)0.00