{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/interpreting-and-explaining-deep-neural","title":"AudioMNIST: Exploring Explainable Artificial Intelligence for Audio Analysis on a Simple Benchmark","arxiv_id":"1807.03418","date":"2018-07-09","proceeding":null,"authors":["Sören Becker","Johanna Vielhaben","Marcel Ackermann","Klaus-Robert Müller","Sebastian Lapuschkin","Wojciech Samek"],"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 visual ones in a human user study.","url_abs":"https://arxiv.org/abs/1807.03418v3","url_pdf":"https://arxiv.org/pdf/1807.03418v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"interpreting-and-explaining-deep-neural","repo_url":"https://github.com/soerenab/AudioMNIST","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"interpreting-and-explaining-deep-neural","repo_url":"https://github.com/MorenoLaQuatra/ARCH","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"interpreting-and-explaining-deep-neural","repo_url":"https://github.com/shenchenyi/SpeakerData","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"xai","task_name":"Explainable Artificial Intelligence (XAI)"},{"task_slug":"explainable-artificial-intelligence","task_name":"Explainable artificial intelligence"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"feature-selection","task_name":"feature selection"}],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.03418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.03418"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shenchenyi/SpeakerData","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/soerenab/AudioMNIST","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MorenoLaQuatra/ARCH","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_honours":1,"ran_fixture":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"59a4adcdf063c437","entry":"butter_bandpass","repo":"soerenab/AudioMNIST","repo_kind":"official","path":"recording_scripts/adjustCuts.py","file_url":"https://github.com/soerenab/AudioMNIST/blob/HEAD/recording_scripts/adjustCuts.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"59a4adcdf063c437"}},{"code_sha256_prefix":"62a2fe294beb605d","entry":"butter_bandpass_filter","repo":"soerenab/AudioMNIST","repo_kind":"official","path":"recording_scripts/adjustCuts.py","file_url":"https://github.com/soerenab/AudioMNIST/blob/HEAD/recording_scripts/adjustCuts.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"62a2fe294beb605d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}