{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T20:23:28Z","timestamp":1790713408482,"version":"4.1.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414405","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"556-560","source":"Crossref","is-referenced-by-count":26,"title":["Multi-Task Self-Supervised Pre-Training for Music Classification"],"prefix":"10.1109","author":[{"given":"Ho-Hsiang","family":"Wu","sequence":"first","affiliation":[{"name":"New York University,Music and Audio Research Laboratory,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chieh-Chi","family":"Kao","sequence":"additional","affiliation":[{"name":"Amazon,Alexa Speech"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingming","family":"Tang","sequence":"additional","affiliation":[{"name":"Amazon,Alexa Speech"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Sun","sequence":"additional","affiliation":[{"name":"Amazon,Alexa Speech"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian","family":"McFee","sequence":"additional","affiliation":[{"name":"New York University,Music and Audio Research Laboratory,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan Pablo","family":"Bello","sequence":"additional","affiliation":[{"name":"New York University,Music and Audio Research Laboratory,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Wang","sequence":"additional","affiliation":[{"name":"Amazon,Alexa Speech"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref30","article-title":"Dlr: Toward a deep learned rhythmic representation for music content analysis","author":"jeong","year":"2017"},{"key":"ref10","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020"},{"key":"ref11","article-title":"Big self-supervised models are strong semi-supervised learners","author":"chen","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2982285"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683426"},{"key":"ref14","first-page":"7482","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","author":"kendall","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2943604"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref18","first-page":"2005","article-title":"Enhancing timbre model using mfcc and its time derivatives for music similarity estimation","author":"de leon","year":"2012","journal-title":"2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO)"},{"key":"ref19","article-title":"Classifying music audio with timbral and chroma features","author":"ellis","year":"2007"},{"key":"ref28","article-title":"The extended ballroom dataset","author":"marchand","year":"2016","journal-title":"ISMIR Late-breaking Session"},{"key":"ref4","first-page":"139","article-title":"Unsupervised learning of local features for music classification","author":"w\u00fclfing","year":"2012","journal-title":"ISMIR"},{"key":"ref27","article-title":"Openmic-2018: An open data-set for multiple instrument recognition","author":"humphrey","year":"2018","journal-title":"ISMIR"},{"key":"ref3","first-page":"141","article-title":"Transfer learning for music classification and regression tasks","author":"choi","year":"2017","journal-title":"ISMIR 2017"},{"key":"ref6","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019"},{"key":"ref29","article-title":"Fma: A dataset for music analysis","author":"defferrard","year":"2017","journal-title":"18th International Society for Music Information Retrieval Conference"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref8","first-page":"14910","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04076-1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref1","article-title":"Automatic tagging using deep convolutional neural networks","author":"choi","year":"2016","journal-title":"ISMIR 2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495219"},{"key":"ref22","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc of ICML"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref24","article-title":"Quasi-recurrent neural networks","author":"bradbury","year":"2017","journal-title":"Proc of ICLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref25","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414405.pdf?arnumber=9414405","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:19:10Z","timestamp":1659485950000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414405\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414405","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}