{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T02:12:31Z","timestamp":1784945551374,"version":"3.55.0"},"reference-count":58,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176227"],"award-info":[{"award-number":["62176227"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2066213"],"award-info":[{"award-number":["U2066213"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["20720210047"],"award-info":[{"award-number":["20720210047"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"JSPS KAKENHI","award":["19H00597"],"award-info":[{"award-number":["19H00597"]}]},{"name":"Research Support Fund of Wakayama University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3306716","type":"journal-article","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T17:25:23Z","timestamp":1692379523000},"page":"3431-3445","source":"Crossref","is-referenced-by-count":3,"title":["Any-to-Any Voice Conversion With Multi-Layer Speaker Adaptation and Content Supervision"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0055-4882","authenticated-orcid":false,"given":"Xuexin","family":"Xu","sequence":"first","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4551-3292","authenticated-orcid":false,"given":"Liang","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5336-6386","authenticated-orcid":false,"given":"Xunquan","family":"Chen","sequence":"additional","affiliation":[{"name":"Graduate School of System Informatics, Kobe University, Kobe, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7510-8859","authenticated-orcid":false,"given":"Pingyuan","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4964-7289","authenticated-orcid":false,"given":"Jie","family":"Lian","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3701-9026","authenticated-orcid":false,"given":"Jinhui","family":"Chen","sequence":"additional","affiliation":[{"name":"Faculty of Systems Engineering, Wakayama University, Wakayama, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0542-0640","authenticated-orcid":false,"given":"Zhihong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1443"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref12","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","author":"qian","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref56","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2960721"},{"key":"ref14","first-page":"7836","article-title":"Unsupervised speech decomposition via triple information bottleneck","author":"qian","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref58","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"wang","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1331"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066047"},{"key":"ref54","first-page":"359","article-title":"Using dynamic time warping to find patterns in time series","volume":"10","author":"berndt","year":"0","journal-title":"Proceedings of the Workshop on Knowledge Discovery in Database"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053854"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413699"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414257"},{"key":"ref51","first-page":"14910","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref50","first-page":"5767","article-title":"Improved training of wasserstein GANs","author":"gulrajani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref48","first-page":"1","article-title":"Rectifier nonlinearities improve neural network acoustic models","author":"maas","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref47","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016"},{"key":"ref42","article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","author":"popov","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-684"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref49","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1830"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2353991"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078543"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-970"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-506"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414851"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053726"},{"key":"ref31","first-page":"6840","article-title":"Denoising diffusion probabilistic models","author":"ho","year":"0","journal-title":"Proc 34th Int Conf Neural Inf Process Syst"},{"key":"ref30","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2307"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462342"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1250\/ast.11.71"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2512"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref24","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"0","journal-title":"Proc Int Conf Med Image Comput Comput - Assist Interv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_19"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-24"},{"key":"ref25","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"veaux","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1356"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-137"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746430"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076867"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688010"},{"key":"ref29","article-title":"Auto-encoding variational bayes","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10224343.pdf?arnumber=10224343","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:37:40Z","timestamp":1699904260000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10224343\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3306716","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}