{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T18:54:13Z","timestamp":1770317653149,"version":"3.49.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094670","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":16,"title":["Toward Universal Text-To-Music Retrieval"],"prefix":"10.1109","author":[{"given":"SeungHeon","family":"Doh","sequence":"first","affiliation":[{"name":"KAIST,Graduate School of Culture Technology,South Korea"}]},{"given":"Minz","family":"Won","sequence":"additional","affiliation":[{"name":"ByteDance,USA"}]},{"given":"Keunwoo","family":"Choi","sequence":"additional","affiliation":[{"name":"Gaudio Lab,South Korea"}]},{"given":"Juhan","family":"Nam","sequence":"additional","affiliation":[{"name":"KAIST,Graduate School of Culture Technology,South Korea"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref12","article-title":"Semi-supervised music tagging transformer","author":"won","year":"2021","journal-title":"ISMIR"},{"key":"ref15","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018"},{"key":"ref14","article-title":"Learning a cross-domain embedding space of vocal and mixed audio with a structure-preserving triplet loss","author":"kim","year":"2021","journal-title":"ISMIR"},{"key":"ref31","article-title":"Supervised and unsupervised learning of audio representations for music understanding","author":"andreas","year":"2022","journal-title":"ISMIR"},{"key":"ref30","article-title":"Music representation learning based on editorial metadata from discogs","author":"alonso-jim\u00e9nez","year":"2022","journal-title":"ISMIR"},{"key":"ref11","article-title":"Contrastive audio-language learning for music","author":"manco","year":"2022","journal-title":"ISMIR"},{"key":"ref10","article-title":"Mulan: A joint embedding of music audio and natural language","author":"huang","year":"2022","journal-title":"ISMIR"},{"key":"ref2","article-title":"Metric learning vs classification for disentangled music representation learning","author":"lee","year":"2020","journal-title":"ISMIR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74851-9_10"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref16","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref19","article-title":"The million song dataset","author":"bertin-mahieux","year":"2011","journal-title":"Proc ISMIR"},{"key":"ref18","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"Proceedings of NAACL-HLT"},{"key":"ref24","article-title":"The mtg-jamendo dataset for automatic music tagging","author":"bogdanov","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746996"},{"key":"ref26","article-title":"Fma: A dataset for music analysis","author":"defferrard","year":"2016","journal-title":"IS-MIR"},{"key":"ref25","article-title":"The gtzan dataset: Its contents, its faults, their effects on evaluation, and its future use","author":"sturm","year":"2013"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2019.8877462"},{"key":"ref22","article-title":"Codified audio language modeling learns useful representations for music information retrieval","author":"castellon","year":"2021","journal-title":"ISMIR"},{"key":"ref21","article-title":"Evaluation of algorithms using games: The case of music tagging","author":"law","year":"2009","journal-title":"ISMIR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2015.03.004"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2993893"},{"key":"ref29","article-title":"Zero-shot learning and knowledge transfer in music classification and tagging","author":"choi","year":"2019"},{"key":"ref8","article-title":"Multimodal metric learning for tag-based music retrieval","author":"won","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref7","article-title":"Zero-shot learning for audio-based music classification and tagging","author":"choi","year":"2019","journal-title":"Proc ISMIR"},{"key":"ref9","article-title":"Emotion embedding spaces for matching music to stories","author":"won","year":"2021","journal-title":"ISMIR"},{"key":"ref4","article-title":"hey alexa, what’s up?","author":"sciuto","year":"2018","journal-title":"a mixed-methods studies of in-home conversational agent usage \" in Proceedings of the designing interactive systems conference"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.913750"},{"key":"ref6","article-title":"Deep learning for audio-based music classification and tagging: Teaching computers to distinguish rock from bach","author":"nam","year":"2018","journal-title":"IEEE Signal Processing Magazine"},{"key":"ref5","article-title":"Automatic tagging using deep convolutional neural networks","author":"choi","year":"2016","journal-title":"ISMIR"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10094670.pdf?arnumber=10094670","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:02:05Z","timestamp":1700506925000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094670\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094670","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}