{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:34:33Z","timestamp":1763202873264,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447390","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"7015-7019","source":"Crossref","is-referenced-by-count":2,"title":["AttHear: Explaining Audio Transformers Using Attention-Aware NMF"],"prefix":"10.1109","author":[{"given":"Alican","family":"Akman","sequence":"first","affiliation":[{"name":"Imperial College London,GLAM,Department of Computing,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bj\u00f6rn W.","family":"Schuller","sequence":"additional","affiliation":[{"name":"Imperial College London,GLAM,Department of Computing,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479879"},{"article-title":"Interpreting and explaining deep neural networks for classification of audio signals","year":"2019","author":"Becker","key":"ref2"},{"article-title":"Xai-based comparison of input representations for audio event classification","year":"2023","author":"Frommholz","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110309"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094635"},{"article-title":"audioLIME: Listenable Explanations Using Source Separation","volume-title":"13th International Workshop on Machine Learning and Music","author":"Haunschmid","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC48229.2022.9871291"},{"journal-title":"Listen to interpret: Post-hoc interpretability for audio networks with nmf","year":"2022","author":"Parekh","key":"ref8"},{"key":"ref9","article-title":"Algorithms for non-negative matrix factorization","volume":"13","author":"Lee","year":"2000","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref12","article-title":"Wavlm: Large-scale self-supervised pre-training for full stack speech processing","volume":"abs\/2110.13900","author":"Chen","year":"2021","journal-title":"CoRR"},{"key":"ref13","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume":"abs\/1910.05453","author":"Baevski","year":"2019","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383575"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-3007"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3327163"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-44781-0_8"},{"key":"ref20","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","volume":"abs\/1804.03209","author":"Warden","year":"2018","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref22","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"abs\/2006.11477","author":"Baevski","year":"2020","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2022.10.001"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447390.pdf?arnumber=10447390","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:37:22Z","timestamp":1722577042000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447390\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447390","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}