{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:22:33Z","timestamp":1774419753717,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890072","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Aligned Contrastive Learning for Text-to-Music Retrieval"],"prefix":"10.1109","author":[{"given":"Tatsuya","family":"Komatsu","sequence":"first","affiliation":[{"name":"LY Corporation,Tokyo,Japan"}]},{"given":"Hokuto","family":"Munakata","sequence":"additional","affiliation":[{"name":"LY Corporation,Tokyo,Japan"}]},{"given":"Takuya","family":"Hasumi","sequence":"additional","affiliation":[{"name":"LY Corporation,Tokyo,Japan"}]},{"given":"Yusuke","family":"Fujita","sequence":"additional","affiliation":[{"name":"LY Corporation,Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/217279.215273"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74851-9_10"},{"key":"ref3","article-title":"Query-by-blending: A music exploration system blending latent vector representations of lyric word, song audio, and artist","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Watanabe"},{"key":"ref4","article-title":"Metric learning vs classification for disentangled music representation learning","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Lee"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.913750"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2874383"},{"key":"ref7","article-title":"Evaluation of cnn-based automatic music tagging models","author":"Won","year":"2020","journal-title":"Sound and Music Computing"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5745561"},{"key":"ref9","first-page":"59","article-title":"Acoustic event search with an onomatopoeic query: measuring distance between onomatopoeic words and sounds","volume-title":"DCASE Workshop","author":"Ikawa"},{"key":"ref10","article-title":"Language-based audio retrieval with pre-trained models","author":"Mei","year":"2022","journal-title":"DCASE 2022 Challenge, Tech. Rep."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11115"},{"key":"ref12","article-title":"Automatic tagging using deep convolutional neural networks","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Choi"},{"key":"ref13","article-title":"Zero-shot learning for audio-based music classification and tagging","volume-title":"Proc. International Society for Music Information Retrieval Conference (ISMIR)","author":"Choi"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413514"},{"key":"ref15","article-title":"Emotion embedding spaces for matching music to stories","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Won"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746131"},{"key":"ref17","author":"Huang","year":"2022","journal-title":"Mulan: A joint embedding of music audio and natural language"},{"key":"ref18","article-title":"Contrastive audio-language learning for music","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Manco"},{"key":"ref19","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094670"},{"key":"ref23","author":"Oord","year":"2018","journal-title":"Representation learning with contrastive predictive coding"},{"key":"ref24","article-title":"The million song dataset","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Bertin-Mahieux"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2019.8877462"},{"key":"ref26","article-title":"Semi-supervised music tagging transformer","volume-title":"International Society for Music Information Retrieval Conference (ISMIR)","author":"Won"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746996"},{"key":"ref28","author":"Devlin","year":"2018","journal-title":"BERT: Pre-training of deep bidirectional transformers for language understanding"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890072.pdf?arnumber=10890072","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:28Z","timestamp":1774416268000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890072\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890072","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}