{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:59:12Z","timestamp":1764403152967},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746131","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"4583-4587","source":"Crossref","is-referenced-by-count":5,"title":["Learning Music Sequence Representation From Text Supervision"],"prefix":"10.1109","author":[{"given":"Tianyu","family":"Chen","sequence":"first","affiliation":[{"name":"Beihang University,Bdbc,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[{"name":"The Institute of Acoustics of the Chinese Academy of Sciences,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beihang University,Bdbc,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaohan","family":"Huang","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Beihang University,Bdbc,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianxin","family":"Li","sequence":"additional","affiliation":[{"name":"Beihang University,Bdbc,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"ICML"},{"article-title":"A simple long-tailed recognition baseline via vision-language model","year":"2021","author":"ma","key":"ref11"},{"key":"ref12","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533654"},{"article-title":"Audioclip: Extending clip to image, text and audio","year":"2021","author":"guzhov","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4142-3"},{"article-title":"The gtzan dataset: Its contents, its faults, their effects on evaluation, and its future use","year":"2013","author":"sturm","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2478068"},{"article-title":"Music genre classification using machine learning techniques","year":"2018","author":"bahuleyan","key":"ref4"},{"article-title":"Toward interpretable music tagging with self-attention","year":"2019","author":"won","key":"ref3"},{"key":"ref6","article-title":"musicnn: Pre-trained convolutional neural networks for music audio tagging","author":"pons","year":"2019","journal-title":"ISMIR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"ref8","article-title":"Representation learning of music using artist, album, and track information","author":"lee","year":"2019","journal-title":"ICML"},{"key":"ref7","article-title":"Transfer learning by supervised pre-training for audio-based music classification","author":"den oord","year":"2014","journal-title":"ISMIR"},{"key":"ref2","article-title":"End-to-end learning for music audio tagging at scale","author":"pons","year":"2018","journal-title":"ISMIR"},{"key":"ref1","article-title":"Automatic tagging using deep convolutional neural networks","author":"choi","year":"2016","journal-title":"ISMIR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053240"},{"key":"ref20","article-title":"Evaluation of algorithms using games: The case of music tagging","author":"law","year":"2009","journal-title":"ISMIR"},{"key":"ref22","article-title":"Contrastive learning of musical representations","author":"spijkervet","year":"2021","journal-title":"ISMIR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref23","article-title":"Codified audio language modeling learns useful representations for music information retrieval","author":"castellon","year":"2021","journal-title":"ISMIR"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746131.pdf?arnumber=9746131","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:07:34Z","timestamp":1660594054000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746131\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746131","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}