{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:23:10Z","timestamp":1774419790587,"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\/icassp49660.2025.10888814","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Zero-shot Musical Stem Retrieval with Joint-Embedding Predictive Architectures"],"prefix":"10.1109","author":[{"given":"Alain","family":"Riou","sequence":"first","affiliation":[{"name":"Institut Polytechnique de Paris,LTCI, Télécom-Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonin","family":"Gagner\u00e9","sequence":"additional","affiliation":[{"name":"Institut Polytechnique de Paris,LTCI, Télécom-Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ga\u00ebtan","family":"Hadjeres","sequence":"additional","affiliation":[{"name":"Sony AI,Zurich,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Lattner","sequence":"additional","affiliation":[{"name":"Sony Computer Science Laboratories,Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Geoffroy","family":"Peeters","sequence":"additional","affiliation":[{"name":"Institut Polytechnique de Paris,LTCI, Télécom-Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2347135"},{"key":"ref2","article-title":"Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility Estimation","volume-title":"Proceedings of the 25th International Society for Music Information Retrieval Conference","author":"Riou"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref4","first-page":"1575","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"37th International Conference on Machine Learning, ICML 2020","volume":"PartF16814","author":"Chen"},{"key":"ref5","article-title":"Contrastive Learning of Musical Representations","volume-title":"Proceedings of the 22nd International Society for Music Information Retrieval Conference, ISMIR 2021","author":"Spijkervet"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 1824 July 2021, Virtual Event","author":"Radford"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref9","first-page":"424","article-title":"Neural Loop Combiner: Neural Network Models for Assessing the Compatibility of Loops","volume-title":"Proceedings of the 21st International Society for Music Information Retrieval Conference, ISMIR 2020","author":"Chen"},{"key":"ref10","first-page":"781","article-title":"Samplematch: Drum sample retrieval by musical context","volume-title":"Proceedings of the 23rd International Society for Music Information Retrieval Conference, ISMIR 2022, Bengaluru, India, December 4-8, 2022","author":"Lattner"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01499"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097236"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref15","author":"Rafii","year":"2017","journal-title":"The MUSDB18 corpus for music separation"},{"key":"ref16","first-page":"619","article-title":"Moisesdb: A dataset for source separation beyond 4-stems","volume-title":"Proceedings of the 24th International Society for Music Information Retrieval Conference, ISMIR 2023, Milan, Italy, November 5-9, 2023","author":"Pereira"},{"key":"ref17","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021","author":"Dosovitskiy"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095969"},{"key":"ref19","article-title":"Decoupled weight decay regularization","volume-title":"7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019","author":"Loshchilov"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858509"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865704408099"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2205244"},{"key":"ref23","first-page":"565","article-title":"The Harmonix Set: Beats, Downbeats, and Functional Segment Annotations of Western Popular Music","volume-title":"Proceedings of the 20th International Society for Music Information Retrieval Conference","author":"Nieto"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref25","article-title":"Joint beat and downbeat tracking with recurrent neural networks","volume-title":"International Society for Music Information Retrieval Conference","author":"B\u00f6ck"},{"key":"ref26","article-title":"Deconstruct, analyse, reconstruct: How to improve tempo, beat, and downbeat estimation","volume-title":"International Society for Music Information Retrieval Conference","author":"B\u00f6ck"},{"key":"ref27","article-title":"An Efficient State-Space Model for Joint Tempo and Meter Tracking","volume-title":"Proceedings of the 16th International Society for Music Information Retrieval Conference","author":"Krebs"},{"key":"ref28","article-title":"A Contrastive Self-Supervised Learning scheme for beat tracking amenable to few-shot learning","volume-title":"Proceedings of the 25th International Society for Music Information Retrieval Conference","author":"Gagner\u00e9"}],"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\/10888814.pdf?arnumber=10888814","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:41Z","timestamp":1774416281000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888814\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888814","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}