{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:44:13Z","timestamp":1730231053538,"version":"3.28.0"},"reference-count":21,"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\/icassp48485.2024.10447670","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10966-10970","source":"Crossref","is-referenced-by-count":0,"title":["Towards Optimal Voice Disentanglement with Weak Supervision"],"prefix":"10.1109","author":[{"given":"Mohammad Rasool","family":"Izadi","sequence":"first","affiliation":[{"name":"Bose Corporation,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujia","family":"Yan","sequence":"additional","affiliation":[{"name":"University of Rochester,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Bose Corporation,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Stevenson","sequence":"additional","affiliation":[{"name":"University of Notre Dame,IN,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Deep representation learning in speech processing: Challenges, recent advances, and future trends","year":"2020","author":"Latif","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3420937"},{"key":"ref3","first-page":"16251","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","volume":"34","author":"Choi","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","first-page":"18003","article-title":"Contentvec: An improved self-supervised speech representation by disentangling speakers","volume-title":"International Conference on Machine Learning","author":"Qian"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3169627"},{"article-title":"Challenging common assumptions in the unsupervised learning of disentangled representations","volume-title":"International Conference on Machine Learning","author":"Locatello","key":"ref6"},{"key":"ref7","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_33"},{"key":"ref9","first-page":"6348","article-title":"Weakly-supervised disentanglement without compromises","volume-title":"International Conference on Machine Learning","author":"Locatello"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019195"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25063-7_5"},{"journal-title":"Weakly supervised disentanglement with guarantees","year":"2019","author":"Shu","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11867"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/348"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-39940-9_488"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"ref17","first-page":"8650","article-title":"Global prosody style transfer without text transcriptions","volume-title":"International Conference on Machine Learning","author":"Qian"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-349"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1873"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"}],"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\/10447670.pdf?arnumber=10447670","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:56:42Z","timestamp":1722578202000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447670\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447670","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}