{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T16:48:58Z","timestamp":1765039738945},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447564","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1036-1040","source":"Crossref","is-referenced-by-count":2,"title":["Unsupervised Pitch-Timbre Disentanglement of Musical Instruments Using a Jacobian Disentangled Sequential Autoencoder"],"prefix":"10.1109","author":[{"given":"Yin-Jyun","family":"Luo","sequence":"first","affiliation":[{"name":"Queen Mary University of London,Centre for Digital Music"}]},{"given":"Sebastian","family":"Ewert","sequence":"additional","affiliation":[{"name":"Spotify"}]},{"given":"Simon","family":"Dixon","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,Centre for Digital Music"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-39593-2_1"},{"key":"ref2","article-title":"Unsupervised learning of disentangled representations from video","author":"Denton","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref3","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"Hsu","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Toward controlled generation of text","volume-title":"Int. Conference on Machine Learning","author":"Hu","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414235"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054582"},{"article-title":"Unsupervised disentanglement of pitch and timbre for isolated musical instrument sounds","volume-title":"Int. Society for Music Information Retrieval Conference","author":"Luo","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095009"},{"article-title":"Disentangled sequential autoencoder","volume-title":"Int. Conference on Machine Learning","author":"Li","key":"ref9"},{"key":"ref10","article-title":"Contrastively disentangled sequential variational autoencoder","author":"Bai","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00657"},{"article-title":"Disentangled recurrent Wasserstein autoencoder","volume-title":"Int. Conference on Learning Representations","author":"Han","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00808"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747272"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9979893"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022787"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/458"},{"article-title":"Auto-encoding variational bayes","volume-title":"Int. Conference on Learning Representations","author":"Kingma","key":"ref18"},{"article-title":"Challenging common assumptions in the unsupervised learning of disentangled representations","volume-title":"Int. Conference on Machine Learning","author":"Locatello","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2856090"},{"article-title":"Overcoming the disentanglement vs reconstruction trade-off via Jacobian supervision","volume-title":"Int. Conference on Learning Representations","author":"Lezama","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2271648"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447564.pdf?arnumber=10447564","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:48:45Z","timestamp":1722577725000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447564\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447564","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}