{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T19:03:19Z","timestamp":1778785399136,"version":"3.51.4"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3358049","type":"journal-article","created":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T18:44:17Z","timestamp":1706121857000},"page":"1392-1405","source":"Crossref","is-referenced-by-count":14,"title":["Tackling Interpretability in Audio Classification Networks With Non-negative Matrix Factorization"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4762-6998","authenticated-orcid":false,"given":"Jayneel","family":"Parekh","sequence":"first","affiliation":[{"name":"Laboratoire de Traitement et Communication de l'Information (LTCI), Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2251-7436","authenticated-orcid":false,"given":"Sanjeel","family":"Parekh","sequence":"additional","affiliation":[{"name":"Laboratoire de Traitement et Communication de l'Information (LTCI), Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1925-3337","authenticated-orcid":false,"given":"Pavlo","family":"Mozharovskyi","sequence":"additional","affiliation":[{"name":"Laboratoire de Traitement et Communication de l'Information (LTCI), Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4960-0010","authenticated-orcid":false,"given":"Ga\u00ebl","family":"Richard","sequence":"additional","affiliation":[{"name":"Laboratoire de Traitement et Communication de l'Information (LTCI), Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8353-0589","authenticated-orcid":false,"given":"Florence","family":"d'Alch\u00e9-Buc","sequence":"additional","affiliation":[{"name":"Laboratoire de Traitement et Communication de l'Information (LTCI), Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28954-6_14"},{"key":"ref2","article-title":"On the robustness of interpretability methods","author":"Alvarez-Melis","year":"2018"},{"key":"ref3","first-page":"2473","article-title":"You shouldnt trust me: Learning models which conceal unfairness from multiple explanation methods","volume-title":"Proc. ECAI","author":"Dimanov","year":"2020"},{"issue":"177","key":"ref4","first-page":"1","article-title":"All models are wrong, but many are useful: Learning a variables importance by studying an entire class of prediction models simultaneously","volume":"20","author":"Fisher","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1214\/21-SS133"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0048-x"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1121\/1.408434"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1538"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1121\/1.1631945"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479879"},{"key":"ref11","first-page":"556","article-title":"Algorithms for non-negative matrix factorization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee","year":"2001"},{"key":"ref12","first-page":"35270","article-title":"Listen to interpret: Post-hoc interpretability for audio networks with NM","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Parekh","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10070850"},{"key":"ref14","first-page":"438","article-title":"Openmic-2018: An open data-set for multiple instrument recognition","volume-title":"Proc. ISMIR","author":"Humphrey","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref16","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lundberg","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314229"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.7312\/haza92762-003"},{"key":"ref19","article-title":"Smoothgrad: Removing noise by adding noise","author":"Smilkov","year":"2017"},{"key":"ref20","article-title":"Restricting the flow: Information bottlenecks for attribution","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schulz","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2017.10.011"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1042"},{"key":"ref24","article-title":"Differentiable rule induction with learned relational features","author":"Kusters","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11771"},{"key":"ref28","first-page":"8928","article-title":"This looks like that: Deep learning for interpretable image recognition","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Chen","year":"2019"},{"key":"ref29","first-page":"24273","article-title":"A framework to learn with interpretation","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Parekh","year":"2021"},{"key":"ref30","first-page":"2668","article-title":"Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (TCAV)","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2018"},{"key":"ref31","first-page":"9277","article-title":"Towards automatic concept-based explanations","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Ghorbani","year":"2019"},{"key":"ref32","first-page":"20554","article-title":"On concept-based explanations in deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yeh","year":"2019"},{"key":"ref33","article-title":"Interpreting and explaining deep neural networks for classification of audio signals","author":"Becker","year":"2018"},{"key":"ref34","article-title":"Toward interpretable music tagging with self-attention","author":"Won","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2341"},{"key":"ref36","first-page":"537","article-title":"Local interpretable model-agnostic explanations for music content analysis","volume-title":"Proc. ISMIR","author":"Mishra","year":"2017"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207444"},{"key":"ref38","article-title":"Audiolime: Listenable explanations using source separation","author":"Haunschmid","year":"2020"},{"key":"ref39","first-page":"246","article-title":"Tracing back music emotion predictions to sound sources and intuitive perceptual qualities","volume-title":"Proc. Sound Music Comput.","volume":"18","author":"Chowdhury","year":"2021"},{"key":"ref40","first-page":"876","article-title":"Concept-based techniques for musicologist-friendly explanations in a deep music classifier","volume-title":"Proc. ISMIR","author":"Foscarin","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30110-3_63"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518538"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.08.009"},{"key":"ref44","first-page":"187","article-title":"Real-time transcription and separation of drum recordings based on NMF decomposition","volume-title":"Proc. DAFx","author":"Dittmar","year":"2014"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366617"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73031-8_1"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2690570"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_3"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937237"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177933"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170034"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1121\/1.1910396"},{"key":"ref53","first-page":"13","article-title":"Sparse NMFhalf-baked or well done?","volume":"11","author":"Roux","year":"2015"},{"key":"ref54","first-page":"2127","article-title":"Attention-based deep multiple instance learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ilse","year":"2018"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.33682\/j5zw-2t88"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462200"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref59","article-title":"CRNNs for urban sound tagging with spatiotemporal context","author":"Arnault","year":"2020"},{"key":"ref60","article-title":"Receptive-field regularized cnns for music classification and tagging","author":"Koutini","year":"2020"},{"key":"ref61","article-title":"Sonyc-ust-v2: An urban sound tagging dataset with spatiotemporal context","author":"Cartwright","year":"2020"},{"key":"ref62","first-page":"1","article-title":"Adam: A. method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17358"},{"key":"ref64","first-page":"7775","article-title":"Towards robust interpretability with self-explaining neural networks","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Alvarez-Melis","year":"2018"},{"issue":"25792605","key":"ref65","first-page":"2579","article-title":"Visualizing high-dimensional data using t-SNE","volume":"9","author":"LJPvd","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.240"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10413597.pdf?arnumber=10413597","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T08:59:24Z","timestamp":1709456364000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10413597\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3358049","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}