{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T13:34:28Z","timestamp":1783085668271,"version":"3.54.6"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science (JSPS) within Grant-in-Aid for Scientific Research","doi-asserted-by":"publisher","award":["19H04172"],"award-info":[{"award-number":["19H04172"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3265807","type":"journal-article","created":{"date-parts":[[2023,4,10]],"date-time":"2023-04-10T19:24:31Z","timestamp":1681154671000},"page":"36579-36604","source":"Crossref","is-referenced-by-count":11,"title":["Embedding-Based Music Emotion Recognition Using Composite Loss"],"prefix":"10.1109","volume":"11","author":[{"given":"Naoki","family":"Takashima","sequence":"first","affiliation":[{"name":"Graduate School of Science and Engineering, Kindai University, Higashiosaka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2110-4207","authenticated-orcid":false,"given":"Fr\u00e9d\u00e9ric","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Medical Informatics, University of Lübeck, Lübeck, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcin","family":"Grzegorzek","sequence":"additional","affiliation":[{"name":"Institute of Medical Informatics, University of Lübeck, Lübeck, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1843-5152","authenticated-orcid":false,"given":"Kimiaki","family":"Shirahama","sequence":"additional","affiliation":[{"name":"Faculty of Informatics, Kindai University, Higashiosaka, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-021-0569-4"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jestch.2020.10.009"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/02699939208411068"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2885744"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3106232"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3218591"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2018.00-21"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3387164"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3281746"},{"key":"ref12","article-title":"Emotion embedding spaces for matching music to stories","author":"Won","year":"2021","journal-title":"arXiv:2111.13468"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s13278-021-00821-4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3071082"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-49666-1_11"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1180639.1180665"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413514"},{"key":"ref18","first-page":"1247","article-title":"Deep canonical correlation analysis","volume-title":"Proc. ICML","author":"Andrew"},{"issue":"220","key":"ref19","first-page":"17","article-title":"Image-caption retrieval by embedding to Gaussian distribution","volume-title":"IEICE Tech. Rep.","volume":"118","author":"Hama","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967212"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0173392"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206037"},{"key":"ref23","first-page":"1","article-title":"A MATLAB toolbox for musical feature extraction from audio","volume-title":"Proc. DAFx","author":"Lartillot"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3032373"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2724515"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2820691"},{"key":"ref28","article-title":"Stacked convolutional and recurrent neural networks for music emotion recognition","author":"Malik","year":"2017","journal-title":"arXiv:1706.02292"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2918739"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-08192-x"},{"key":"ref31","article-title":"Transfer learning for music classification and regression tasks","author":"Choi","year":"2017","journal-title":"arXiv:1703.09179"},{"key":"ref32","article-title":"Comparison and analysis of deep audio embeddings for music emotion recognition","author":"Koh","year":"2021","journal-title":"arXiv:2104.06517"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11584-7"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-022-00230-z"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911513"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064164"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2118752"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2628794"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2014.2333095"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471639"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2397457"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178059"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2415212"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101263"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959550"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2723575"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1459359.1459550"},{"key":"ref49","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv:1412.3555"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref53","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"Kiros","year":"2014","journal-title":"arXiv:1411.2539"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3637870"},{"key":"ref55","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref56","first-page":"325","article-title":"Feature learning in dynamic environments: Modeling the acoustic structure of musical emotion","volume-title":"Proc. ISMIR","author":"Schmidt"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854637"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552956"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390733"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207212"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s12046-020-1313-8"},{"key":"ref62","first-page":"310","article-title":"The multiple voices of musical emotions: Source separation for improving music emotion recognition models and their interpretability","volume-title":"Proc. ISMIR","author":"Berardinis"},{"key":"ref63","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3390\/technologies9010002"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.08.005"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3025777"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10097747.pdf?arnumber=10097747","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T23:12:27Z","timestamp":1709248347000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097747\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3265807","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}