{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T14:18:35Z","timestamp":1765808315715,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T00:00:00Z","timestamp":1695168000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"EU Horizon 2020 iToBoS","award":["965221"],"award-info":[{"award-number":["965221"]}]},{"name":"German Research Foundation","award":["DFG KI-FOR 5363"],"award-info":[{"award-number":["DFG KI-FOR 5363"]}]},{"name":"EU Horizon Europe TEMA","award":["101093003"],"award-info":[{"award-number":["101093003"]}]},{"name":"ProFIT BerDiBa","award":["0174498"],"award-info":[{"award-number":["0174498"]}]},{"name":"BMBF SyReal","award":["01IS21069B"],"award-info":[{"award-number":["01IS21069B"]}]},{"name":"BMBF BIFOLD","award":["01IS18025A"],"award-info":[{"award-number":["01IS18025A"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,9,20]]},"DOI":"10.1145\/3617233.3617265","type":"proceedings-article","created":{"date-parts":[[2023,12,30]],"date-time":"2023-12-30T06:05:32Z","timestamp":1703916332000},"page":"126-132","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["XAI-based Comparison of Audio Event Classifiers with different Input Representations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3600-1028","authenticated-orcid":false,"given":"Annika","family":"Frommholz","sequence":"first","affiliation":[{"name":"Fraunhofer Heinrich Hertz Institute, DE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3352-0473","authenticated-orcid":false,"given":"Fabian","family":"Seipel","sequence":"additional","affiliation":[{"name":"Technical University Berlin, DE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0762-7258","authenticated-orcid":false,"given":"Sebastian","family":"Lapuschkin","sequence":"additional","affiliation":[{"name":"Fraunhofer Heinrich Hertz Institute, DE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6283-3265","authenticated-orcid":false,"given":"Wojciech","family":"Samek","sequence":"additional","affiliation":[{"name":"Fraunhofer Heinrich Hertz Institute, DE and Technical University Berlin, Germany and Berlin Institute for the Foundations of Learning and Data (BIFOLD), Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9399-5710","authenticated-orcid":false,"given":"Johanna","family":"Vielhaben","sequence":"additional","affiliation":[{"name":"Fraunhofer Heinrich Hertz Institute, DE"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,12,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","unstructured":"Sajjad Abdoli Patrick Cardinal and Alessandro\u00a0Lameiras Koerich. 2019. End-to-End Environmental Sound Classification using a 1D Convolutional Neural Network. https:\/\/doi.org\/10.48550\/ARXIV.1904.08990","DOI":"10.48550\/ARXIV.1904.08990"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","unstructured":"Christopher\u00a0J. Anders David Neumann Wojciech Samek Klaus-Robert M\u00fcller and Sebastian Lapuschkin. 2021. Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit CoRelAy and ViRelAy. https:\/\/doi.org\/10.48550\/ARXIV.2106.13200","DOI":"10.48550\/ARXIV.2106.13200"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"S\u00f6ren Becker Marcel Ackermann Sebastian Lapuschkin Klaus-Robert M\u00fcller and Wojciech Samek. 2018. Interpreting and Explaining Deep Neural Networks for Classification of Audio Signals. https:\/\/doi.org\/10.48550\/ARXIV.1807.03418","DOI":"10.48550\/ARXIV.1807.03418"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","unstructured":"Marco Colussi and Stavros Ntalampiras. 2021. Interpreting deep urban sound classification using Layer-wise Relevance Propagation. https:\/\/doi.org\/10.48550\/ARXIV.2111.10235","DOI":"10.48550\/ARXIV.2111.10235"},{"key":"e_1_3_2_1_6_1","volume-title":"CNN Architectures for Large-Scale Audio Classification. In International Conference on Acoustics, Speech and Signal Processing (ICASSP). https:\/\/arxiv.org\/abs\/1609","author":"Hershey Shawn","year":"2017","unstructured":"Shawn Hershey, Sourish Chaudhuri, Daniel P.\u00a0W. Ellis, Jort\u00a0F. Gemmeke, Aren Jansen, Channing Moore, Manoj Plakal, Devin Platt, Rif\u00a0A. Saurous, Bryan Seybold, Malcolm Slaney, Ron Weiss, and Kevin Wilson. 2017. CNN Architectures for Large-Scale Audio Classification. In International Conference on Acoustics, Speech and Signal Processing (ICASSP). https:\/\/arxiv.org\/abs\/1609.09430"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","unstructured":"Andrew\u00a0G. Howard Menglong Zhu Bo Chen Dmitry Kalenichenko Weijun Wang Tobias Weyand Marco Andreetto and Hartwig Adam. 2017. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. https:\/\/doi.org\/10.48550\/ARXIV.1704.04861","DOI":"10.48550\/ARXIV.1704.04861"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206975"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-384"},{"key":"e_1_3_2_1_11_1","volume-title":"Advances in Neural Information Processing Systems, F.\u00a0Pereira, C.J. Burges, L.\u00a0Bottou, and K","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey\u00a0E Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In Advances in Neural Information Processing Systems, F.\u00a0Pereira, C.J. Burges, L.\u00a0Bottou, and K.Q. Weinberger (Eds.). Vol.\u00a025. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2012\/file\/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","unstructured":"Jongpil Lee Taejun Kim Jiyoung Park and Juhan Nam. 2017. Raw Waveform-based Audio Classification Using Sample-level CNN Architectures. https:\/\/doi.org\/10.48550\/ARXIV.1712.00866","DOI":"10.48550\/ARXIV.1712.00866"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28954-6_10"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.11.008"},{"key":"e_1_3_2_1_15_1","unstructured":"Geoffroy Peeters. 2004. A large set of audio features for sound description (similarity and classification) in the CUIDADO project. CUIDADO Ist Project Report 54 0 (2004) 1\u201325."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2015.7324337"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105000"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","unstructured":"Thomas Rojat Rapha\u00ebl Puget David Filliat Javier Del\u00a0Ser Rodolphe Gelin and Natalia D\u00edaz-Rodr\u00edguez. 2021. Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey. https:\/\/doi.org\/10.48550\/ARXIV.2104.00950","DOI":"10.48550\/ARXIV.2104.00950"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177954"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553247"},{"key":"e_1_3_2_1_22_1","unstructured":"Hongyi Sun Xinyi Liu Kecheng Xu Jinghao Miao and Qi Luo. 2021. Emergency Vehicles Audio Detection and Localization in Autonomous Driving. arxiv:2109.14797\u00a0[cs.SD]"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952651"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.3390\/jsan10040072"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","unstructured":"Johanna Vielhaben Sebastian Lapuschkin Gr\u00e9goire Montavon and Wojciech Samek. 2023. Explainable AI for Time Series via Virtual Inspection Layers. https:\/\/doi.org\/10.48550\/ARXIV.2303.06365","DOI":"10.48550\/ARXIV.2303.06365"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCSP48568.2020.9182160"},{"key":"e_1_3_2_1_27_1","unstructured":"Luyu Wang and Aaron van\u00a0den Oord. 2021. Multi-Format Contrastive Learning of Audio Representations. arxiv:2103.06508\u00a0[cs.SD]"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"S. Weinzierl. 2009. Handbuch der Audiotechnik. Springer Berlin Heidelberg.","DOI":"10.1007\/978-3-540-34301-1"},{"key":"e_1_3_2_1_29_1","volume-title":"ADADELTA: An Adaptive Learning Rate Method. arxiv:1212.5701\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1212.5701v1","author":"Zeiler D.","year":"2012","unstructured":"Matthew\u00a0D. Zeiler. 2012. ADADELTA: An Adaptive Learning Rate Method. arxiv:1212.5701\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1212.5701v1"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10070850"}],"event":{"name":"CBMI 2023: 20th International Conference on Content-based Multimedia Indexing","acronym":"CBMI 2023","location":"Orleans France"},"container-title":["20th International Conference on Content-based Multimedia Indexing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3617233.3617265","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3617233.3617265","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T17:00:11Z","timestamp":1756486811000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3617233.3617265"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,20]]},"references-count":30,"alternative-id":["10.1145\/3617233.3617265","10.1145\/3617233"],"URL":"https:\/\/doi.org\/10.1145\/3617233.3617265","relation":{},"subject":[],"published":{"date-parts":[[2023,9,20]]},"assertion":[{"value":"2023-12-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}