{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:13Z","timestamp":1775229913911,"version":"3.50.1"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JSPS KAKENHI","award":["JP21H00906"],"award-info":[{"award-number":["JP21H00906"]}]},{"name":"JSPS KAKENHI","award":["19H00597"],"award-info":[{"award-number":["19H00597"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3222646","type":"journal-article","created":{"date-parts":[[2022,11,16]],"date-time":"2022-11-16T20:39:39Z","timestamp":1668631179000},"page":"7480-7493","source":"Crossref","is-referenced-by-count":7,"title":["Speaker-Independent Emotional Voice Conversion via Disentangled Representations"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5336-6386","authenticated-orcid":false,"given":"Xunquan","family":"Chen","sequence":"first","affiliation":[{"name":"Graduate School of System Informatics, Kobe University, Kobe, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0055-4882","authenticated-orcid":false,"given":"Xuexin","family":"Xu","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3701-9026","authenticated-orcid":false,"given":"Jinhui","family":"Chen","sequence":"additional","affiliation":[{"name":"Prefectural University of Hiroshima, Hiroshima, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0542-0640","authenticated-orcid":false,"given":"Zhizhong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5005-7679","authenticated-orcid":false,"given":"Tetsuya","family":"Takiguchi","sequence":"additional","affiliation":[{"name":"Graduate School of System Informatics, Kobe University, Kobe, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4496-2028","authenticated-orcid":false,"given":"Edwin R.","family":"Hancock","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of York, York, U.K."}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054681"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1515\/lp-2013-0003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-112"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5923\/j.ajsp.20120205.06"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2014.7041640"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICIS.2016.7550889"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-33"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054579"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1647"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2878"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-781"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i7.16753"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3032037"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2938007"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2937768"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3063605"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3087026"},{"key":"ref19","first-page":"5210","article-title":"AUTOVC: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref21","first-page":"294","article-title":"VOICEMIXER: Adversarial voice style mixup","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Lee","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_13"},{"key":"ref23","first-page":"5102","article-title":"Domain agnostic learning with disentangled representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Peng","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054591"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414226"},{"key":"ref26","article-title":"Improving zero-shot voice style transfer via disentangled representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yuan","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref28","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Goodfellow","year":"2014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3065460"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3071243"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3056645"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3141267"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2014"},{"key":"ref37","first-page":"531","article-title":"Mutual information neural estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Belghazi","year":"2018"},{"key":"ref38","article-title":"Representation learning with contrastive predictive coding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Oord","year":"2018"},{"key":"ref39","first-page":"1779","article-title":"CLUB: A contrastive log-ratio upper bound of mutual information","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cheng","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.3160280102"},{"key":"ref41","first-page":"5769","article-title":"Improved training of wasserstein GANs","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Gulrajani","year":"2017"},{"key":"ref42","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref44","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"Ulyanov","year":"2016"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1830"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref50","first-page":"1","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"30","author":"Maas","year":"2013"},{"key":"ref51","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Kumar","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1190"},{"key":"ref53","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit [sound]","author":"Veaux","year":"2017"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"issue":"11","key":"ref57","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09953321.pdf?arnumber=9953321","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:15:34Z","timestamp":1705018534000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9953321\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3222646","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}