{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:29:57Z","timestamp":1775503797397,"version":"3.50.1"},"reference-count":31,"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"}],"funder":[{"DOI":"10.13039\/100014013","name":"UK Research and Innovation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746996","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"456-460","source":"Crossref","is-referenced-by-count":21,"title":["Learning Music Audio Representations Via Weak Language Supervision"],"prefix":"10.1109","author":[{"given":"Ilaria","family":"Manco","sequence":"first","affiliation":[{"name":"Queen Mary University of London,School of EECS,London,U.K."}]},{"given":"Emmanouil","family":"Benetos","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,School of EECS,London,U.K."}]},{"given":"Elio","family":"Quinton","sequence":"additional","affiliation":[{"name":"Universal Music Group,Music & Audio Machine Learning Lab,London,U.K."}]},{"given":"Gyorgy","family":"Fazekas","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,School of EECS,London,U.K."}]}],"member":"263","reference":[{"key":"ref31","article-title":"MediaEval 2020 emotion and theme recognition in music task: Loss function approaches for multi-label music tagging","author":"knox","year":"2020","journal-title":"CEUR Workshop Proceedings"},{"key":"ref30","article-title":"Representation Learning of Music Using Artist Labels","author":"park","year":"2018","journal-title":"Proceedings of the 19th ISMIR conference"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414405"},{"key":"ref11","article-title":"Codified audio language modeling learns useful representations for music information retrieval","author":"castellon","year":"2021","journal-title":"Proceedings of the 22nd ISMIR Conference"},{"key":"ref12","first-page":"13","article-title":"ViLBERT: Pre-training Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","author":"lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"UNITER: UNiversal Image-TExt Representation Learning","author":"chen","year":"2020","journal-title":"European Conference on Computer Vision"},{"key":"ref14","article-title":"COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations","author":"favory","year":"2020","journal-title":"International Conference on Machine Learning (ICML) Workshop on Self-supervised learning in Audio and Speech"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414638"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3071082"},{"key":"ref17","first-page":"331","article-title":"Evaluation of CNN-based Automatic Music Tagging Models","author":"won","year":"2020","journal-title":"Proceedings of the 17th Sound and Music Computing Conference"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053240"},{"key":"ref19","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref28","article-title":"MediaEval 2019: Emotion and theme recognition in music using jamendo","author":"bogdanov","year":"2019","journal-title":"CEUR Workshop Proceedings"},{"key":"ref4","article-title":"Transfer Learning In MIR: Sharing Learned Latent Representations For Music Audio Classification And Similarity","author":"hamel","year":"2013","journal-title":"Proceedings of the 14th ISMIR Conference"},{"key":"ref27","article-title":"Neural audio synthesis of musical notes with WaveNet autoencoders","author":"engel","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1007\/978-3-030-58558-7_29","article-title":"Big Transfer (BiT): General Visual Representation Learning","volume":"12350","author":"kolesnikov","year":"2020","journal-title":"Computer Vision - ECCV 2020"},{"key":"ref6","article-title":"Transfer Learning for Music Classification and Regression Tasks","author":"choi","year":"2017","journal-title":"Proceedings of the 18th ISMIR Conference"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2506364.2506365"},{"key":"ref5","article-title":"Transfer learning by supervised pre-training for audio-based music classification","author":"van den oord","year":"2014","journal-title":"Proceedings of the 15th ISMIR Conference"},{"key":"ref8","article-title":"Exploring customer reviews for music genre classification and evolutionary studies","author":"oramas","year":"2016","journal-title":"Proceedings of The 17th ISMIR Conference"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2713830"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.2985586"},{"key":"ref9","article-title":"Contrastive Learning of Musical Representations","author":"spijkervet","year":"2021","journal-title":"arXiv preprint arXiv 2103 05767"},{"key":"ref1","first-page":"1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2016.7500246"},{"key":"ref22","article-title":"A Simple Framework for Contrastive Learning of Visual Representations","author":"chen","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref21","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018"},{"key":"ref24","article-title":"The MTG-Jamendo Dataset for Automatic Music Tagging","author":"bogdanov","year":"2019","journal-title":"Machine learning for music discovery workshop international conference on machine learning (icml)"},{"key":"ref23","article-title":"Evaluation of algorithms using games: The case of music tagging","author":"law","year":"2009","journal-title":"Proceedings of the 10th ISMIR Conference"},{"key":"ref26","article-title":"FMA: A dataset for music analysis","author":"defferrard","year":"2017","journal-title":"Proceedings of the 18th ISMIR Conference"},{"key":"ref25","article-title":"The million song dataset","author":"bertin-mahieux","year":"2011","journal-title":"Proceedings of the 12th ISMIR Conference"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"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\/09746996.pdf?arnumber=9746996","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:11:34Z","timestamp":1660594294000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746996\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746996","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}