{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:12:30Z","timestamp":1774419150601,"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"}],"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889639","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":["Hybrid Losses for Hierarchical Embedding Learning"],"prefix":"10.1109","author":[{"given":"Haokun","family":"Tian","sequence":"first","affiliation":[{"name":"Queen Mary University of London,Center for Digital Music,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Lattner","sequence":"additional","affiliation":[{"name":"Sony Computer Science Laboratories,Music Team,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"McFee","sequence":"additional","affiliation":[{"name":"New York University,Music and Audio Research Laboratory,New York,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charalampos","family":"Saitis","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,Center for Digital Music,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01252"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"NeurIPS","author":"Krizhevsky"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref6","article-title":"Leveraging hierarchical structures for few-shot musical instrument recognition","author":"Garcia","year":"2021","journal-title":"ISMIR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.126"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682341"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747690"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3291506"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746907"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094943"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3379894"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref19","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.309"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.307"},{"key":"ref23","article-title":"Orchideasol: a dataset of extended instrumental techniques for computer-aided orchestration","author":"Cella","year":"2020","journal-title":"ICMC"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2943604"},{"key":"ref25","article-title":"Samplematch: Drum sample retrieval by musical context","author":"Lattner","year":"2022","journal-title":"ISMIR"},{"key":"ref26","article-title":"Singer identity representation learning using self-supervised techniques","author":"Torres","year":"2023","journal-title":"ISMIR"},{"key":"ref27","article-title":"Poincar\u00e9 embeddings for learning hierarchical representations","volume-title":"NeurIPS","author":"Nickel"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00645"}],"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\/10889639.pdf?arnumber=10889639","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:20:50Z","timestamp":1774416050000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889639\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889639","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}