{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:41:32Z","timestamp":1762368092931,"version":"build-2065373602"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"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":[[2025,8,31]]},"DOI":"10.1109\/mlsp62443.2025.11204308","type":"proceedings-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T17:15:52Z","timestamp":1761326152000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Representation Learning for Music Via Likelihood Factorisation of a Variational Autoencoder"],"prefix":"10.1109","author":[{"given":"Ningzhi","family":"Wang","sequence":"first","affiliation":[{"name":"Queen Mary University of London"}]},{"given":"Daniel","family":"Stoller","sequence":"additional","affiliation":[{"name":"Spotify GmbH,Germany"}]},{"given":"Simon","family":"Dixon","sequence":"additional","affiliation":[{"name":"Queen Mary University of London"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref2","article-title":"Codified audio language modeling learns useful representations for music information retrieval","author":"Castellon","year":"2021","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"MERT: Acoustic music understanding model with large-scale selfsupervised training","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Variational lossy autoencoder","author":"Chen","year":"2016","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"PixelVAE: A latent variable model for natural images","author":"Gulrajani","year":"2016","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Improving VAE-based representation learning","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Conditional image generation with PixelCNN decoders","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"van den Oord","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.09661"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04179-3_6"},{"key":"ref11","article-title":"Contrastive learning of musical representations","author":"Spijkervet","year":"2021","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Supervised and unsupervised learning of audio representations for music understanding","author":"McCallum","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Music-PAW: Learning music representations via hierarchical part-whole interaction and contrast","author":"Yao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International Conference on Machine Learning","author":"Chen","year":"2020"},{"key":"ref15","article-title":"Generating diverse high-fidelity images with VQ-VAE2","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Razavi","year":"2019"},{"key":"ref16","article-title":"PixelCNN++: Improving the PixelCNN with discretized logistic mixture likelihood and other modifications","author":"Salimans","year":"2017","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"316","article-title":"FMA: A dataset for music analysis","volume-title":"Proc. of the International Society for Music Information Retrieval Conference (ISMIR)","author":"Defferrard"},{"key":"ref18","first-page":"387","article-title":"Evaluation of algorithms using games: The case of music tagging","volume-title":"Proceedings of the International Society for Music Information Retrieval (ISMIR) Conference","author":"Law","year":"2009"},{"key":"ref19","first-page":"364","article-title":"Two data sets for tempo estimation and key detection in electronic dance music annotated from user corrections","volume-title":"Proceedings of the 16th International Society for Music Information Retrieval Conference (ISMIR)","author":"Knees","year":"2015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2478068"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2506364.2506365"}],"event":{"name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","start":{"date-parts":[[2025,8,31]]},"location":"Istanbul, Turkiye","end":{"date-parts":[[2025,9,3]]}},"container-title":["2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11204201\/11204202\/11204308.pdf?arnumber=11204308","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:37:16Z","timestamp":1762367836000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11204308\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,31]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/mlsp62443.2025.11204308","relation":{},"subject":[],"published":{"date-parts":[[2025,8,31]]}}}