{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:36:07Z","timestamp":1730230567501,"version":"3.28.0"},"reference-count":30,"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\/icassp48485.2024.10446648","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"531-535","source":"Crossref","is-referenced-by-count":0,"title":["An Explainable Proxy Model for Multilabel Audio Segmentation"],"prefix":"10.1109","author":[{"given":"Th\u00e9o","family":"Mariotte","sequence":"first","affiliation":[{"name":"LIUM, Le Mans Universit&#x00E9;"}]},{"given":"Antonio","family":"Almud\u00e9var","sequence":"additional","affiliation":[{"name":"University of Zaragoza,ViVoLab, Arag&#x00F3;n Institute for Engineering Research (I3A)"}]},{"given":"Marie","family":"Tahon","sequence":"additional","affiliation":[{"name":"LIUM, Le Mans Universit&#x00E9;"}]},{"given":"Alfonso","family":"Ortega","sequence":"additional","affiliation":[{"name":"University of Zaragoza,ViVoLab, Arag&#x00F3;n Institute for Engineering Research (I3A)"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref2","first-page":"1933","article-title":"Learning Effective and Interpretable Semantic Models using Non-Negative Sparse Embedding","volume-title":"Proceedings of COLING 2012","author":"Murphy"},{"key":"ref3","first-page":"1","article-title":"Visualizing deep networks by optimizing with integrated gradients","volume-title":"CVPR Workshops","volume":"2","author":"Qi"},{"key":"ref4","first-page":"537","article-title":"Local interpretable model-agnostic explanations for music content analysis","volume-title":"ISMIR","volume":"53","author":"Mishra"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10070850"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747476"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3358049"},{"key":"ref8","article-title":"Algorithms for non-negative matrix factorization","volume-title":"Advances in neural information processing systems","volume":"13","author":"Lee"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639163"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1155\/2009\/239892"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2285"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053096"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10825"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-019-0155-y"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-019-0152-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-020-00172-6"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-149"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-560"},{"article-title":"Joint speech and overlap detection: a benchmark over multiple audio setup and speech domains","year":"2023","author":"Lebourdais","key":"ref20"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2023.3276171"},{"issue":"TR2015-023","key":"ref24","first-page":"13","article-title":"Sparse nmf\u2013 half-baked or well done?","volume":"11","author":"Le Roux","year":"2015","journal-title":"Mitsubishi Electric Research Labs (MERL), Cambridge, MA, USA, Tech. Rep."},{"key":"ref25","first-page":"283","article-title":"The Albayz\u00edn 2012 audio segmentation evaluation","author":"Ortega","year":"2012","journal-title":"iberspeech"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1208"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2011-1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.29"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414215"},{"article-title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","year":"2018","author":"Bai","key":"ref30"}],"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\/10446648.pdf?arnumber=10446648","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:38:56Z","timestamp":1722573536000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446648\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446648","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}