{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T06:34:16Z","timestamp":1778222056876,"version":"3.51.4"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2015R1C1A1A02036962"],"award-info":[{"award-number":["2015R1C1A1A02036962"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Mag."],"published-print":{"date-parts":[[2019,1]]},"DOI":"10.1109\/msp.2018.2874383","type":"journal-article","created":{"date-parts":[[2018,12,25]],"date-time":"2018-12-25T19:47:00Z","timestamp":1545767220000},"page":"41-51","source":"Crossref","is-referenced-by-count":87,"title":["Deep Learning for Audio-Based Music Classification and Tagging: Teaching Computers to Distinguish Rock from Bach"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2664-2119","authenticated-orcid":false,"given":"Juhan","family":"Nam","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5305-5342","authenticated-orcid":false,"given":"Keunwoo","family":"Choi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1126-0081","authenticated-orcid":false,"given":"Jongpil","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Szu-Yu","family":"Chou","sequence":"additional","affiliation":[]},{"given":"Yi-Hsuan","family":"Yang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","first-page":"23","article-title":"Multi-label music genre classification from audio, text and images using deep features","author":"oramas","year":"0","journal-title":"Proc Int'l Conf on Music Information Retrieval"},{"key":"ref32","first-page":"559","article-title":"A comparison of sound segregation techniques for predominant instrument recognition in musical audio signals","author":"bosch","year":"0","journal-title":"Proc Int Society Music Information Retrieval Conf"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2296076"},{"key":"ref30","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref34","author":"perez","year":"2018","journal-title":"Pandora takes on Spotify with dozens of personalized playlists built using its Music Genome"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref11","first-page":"565","article-title":"Learning sparse feature representations for music annotation and retrieval","author":"nam","year":"0","journal-title":"Proc Int'l Conf on Music Information Retrieval"},{"key":"ref12","first-page":"339","article-title":"Learning features from music audio with deep belief networks","author":"hamel","year":"0","journal-title":"Proc Int'l Conf on Music Information Retrieval"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854950"},{"key":"ref14","first-page":"805","article-title":"Automatic tagging using deep convolutional neural networks","author":"choi","year":"0","journal-title":"Proc Int'l Conf on Music Information Retrieval"},{"key":"ref15","first-page":"220","article-title":"Sample-level deep convolutional neural networks for music auto-tagging using raw waveforms","author":"lee","year":"0","journal-title":"Proc Sound and Music Computing Conf"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/app8010150"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952585"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","article-title":"Squeeze-and-excitation networks","author":"hu","year":"2017"},{"key":"ref28","article-title":"Hit song prediction for pop music by Siamese CNN with ranking loss","author":"yu","year":"2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282049"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2098858"},{"key":"ref6","article-title":"A tutorial on deep learning for music information retrieval","author":"choi","year":"2017"},{"key":"ref29","first-page":"3336","article-title":"Learning to recognize transient sound events using attentional supervision","author":"chou","year":"0","journal-title":"Proc Int Joint Conf Artificial Intelligence"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref8","article-title":"End-to-end learning for music audio tagging at scale","author":"pons","year":"0","journal-title":"Proc Machine Learning Audio Signal Processing Workshop Advances Neural Information Processing Systems"},{"key":"ref7","first-page":"591","article-title":"The Million Song Dataset","author":"bertin-mahieux","year":"0","journal-title":"Proc Int Society Music Information Retrieval Conf"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019472"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-013-0248-5"},{"key":"ref1","first-page":"31","article-title":"Modeling genre with the Music Genome Project: Comparing human-labeled attributes and audio features","author":"prockup","year":"0","journal-title":"Proc Int'l Conf on Music Information Retrieval"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462046"},{"key":"ref22","first-page":"387","article-title":"Evaluation of algorithms using games: The case of music tagging","author":"law","year":"0","journal-title":"Proc Int'l Conf on Music Information Retrieval"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952130"},{"key":"ref24","first-page":"141","article-title":"Transfer learning for music classification and regression tasks","author":"choi","year":"0","journal-title":"Proc Int'l Conf on Music Information Retrieval"},{"key":"ref23","first-page":"316","article-title":"FMA: A dataset for music analysis","author":"defferrard","year":"0","journal-title":"Proc Int'l Conf on Music Information Retrieval"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081710"},{"key":"ref25","first-page":"1048","article-title":"Event localization in music auto-tagging","author":"liu","year":"0","journal-title":"Proc ACM Multimedia Conf"}],"container-title":["IEEE Signal Processing Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/79\/8588402\/08588424.pdf?arnumber=8588424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:49:21Z","timestamp":1657745361000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8588424\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1]]},"references-count":34,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/msp.2018.2874383","relation":{},"ISSN":["1053-5888","1558-0792"],"issn-type":[{"value":"1053-5888","type":"print"},{"value":"1558-0792","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,1]]}}}