{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:25:42Z","timestamp":1774419942441,"version":"3.50.1"},"reference-count":18,"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\/icassp49660.2025.10887608","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":["Diff4Steer: Steerable Diffusion Prior for Generative Music Retrieval with Semantic Guidance"],"prefix":"10.1109","author":[{"given":"Xuchan","family":"Bao","sequence":"first","affiliation":[{"name":"University of Toronto, Google"}]},{"given":"Judith Yue","family":"Li","sequence":"additional","affiliation":[{"name":"University of Toronto, Google"}]},{"given":"Zhong","family":"Yi Wan","sequence":"additional","affiliation":[{"name":"University of Toronto, Google"}]},{"given":"Kun","family":"Su","sequence":"additional","affiliation":[{"name":"University of Toronto, Google"}]},{"given":"Timo","family":"Denk","sequence":"additional","affiliation":[{"name":"University of Toronto, Google"}]},{"given":"Joonseok","family":"Lee","sequence":"additional","affiliation":[{"name":"University of Toronto, Google"}]},{"given":"Dima","family":"Kuzmin","sequence":"additional","affiliation":[{"name":"University of Toronto, Google"}]},{"given":"Fei","family":"Sha","sequence":"additional","affiliation":[{"name":"University of Toronto, Google"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Matrix factorization techniques for recommender systems","volume-title":"Computer","volume":"42","author":"Koren","year":"2009"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1145\/2959100.2959190","article-title":"Deep neural networks for youtube recommendations","volume-title":"Proceedings of the 10th ACM Conference on Recommender Systems","author":"Covington"},{"key":"ref3","first-page":"399","article-title":"A music recommendation system with a dynamic k-means clustering algorithm","volume-title":"Sixth International Conference on Machine Learning and Applications (ICMLA 2007)","author":"Kim"},{"key":"ref4","article-title":"Mulan: A joint embedding of music audio and natural language","author":"Huang","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095889"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380281"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref8","article-title":"Mo\\\u02c6 usai: Text-to-music generation with long-context latent diffusion","author":"Schneider","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3399607"},{"key":"ref10","first-page":"26 565","article-title":"Elucidating the design space of diffusion-based generative models","volume":"35","author":"Karras","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref12","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref13","article-title":"Youtube-8M: A large-scale video classification benchmark","author":"Abu-El-Haija","year":"2016"},{"key":"ref14","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02533"},{"key":"ref16","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref17","article-title":"Sgdr: Stochastic gradient descent with warm restarts","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref18","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"}],"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\/10887608.pdf?arnumber=10887608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:33Z","timestamp":1774416333000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887608\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887608","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}