{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T10:07:55Z","timestamp":1785838075470,"version":"3.56.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054554","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"516-520","source":"Crossref","is-referenced-by-count":72,"title":["Transformer VAE: A Hierarchical Model for Structure-Aware and Interpretable Music Representation Learning"],"prefix":"10.1109","author":[{"given":"Junyan","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gus G.","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dave B.","family":"Carlton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chris N.","family":"Anderson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryan H.","family":"Miyakawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"A reference architecture and score representation for popular music human-computer music performance systems","author":"gold","year":"2011","journal-title":"New Interfaces For Musical Expression"},{"key":"ref11","article-title":"Deep music analogy via latent representation disentanglement","author":"yang","year":"2019","journal-title":"the 20th International Society for Music Information Retrieval Conference ISMIR"},{"key":"ref12","article-title":"Latent constraints: Learning to generate conditionally from unconditional generative models","author":"engel","year":"2017"},{"key":"ref13","article-title":"Musenet","author":"payne","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/727"},{"key":"ref15","article-title":"Tensor2tensor for neural machine translation","author":"vaswani","year":"2018"},{"key":"ref16","article-title":"Tutorial on variational autoencoders","author":"doersch","year":"2016"},{"key":"ref17","first-page":"6","article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework.","volume":"2","author":"higgins","year":"2017","journal-title":"ICLRE"},{"key":"ref18","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref3","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref6","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref5","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref8","article-title":"A hierarchical latent vector model for learning long-term structure in music","author":"roberts","year":"2018"},{"key":"ref7","article-title":"Music transformer","author":"huang","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref2","first-page":"67","article-title":"Computational and collective creativity: Who's being creative?","author":"maher","year":"2012","journal-title":"ICC Citeseer"},{"key":"ref1","article-title":"Nips 2016 tutorial: Generative adversarial networks","author":"goodfellow","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MMRP.2019.00022"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054554.pdf?arnumber=9054554","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:28:05Z","timestamp":1656376085000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054554\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054554","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}