{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T05:13:58Z","timestamp":1748409238610,"version":"3.37.3"},"reference-count":39,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/lsp.2023.3313515","type":"journal-article","created":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T19:22:18Z","timestamp":1694460138000},"page":"1297-1301","source":"Crossref","is-referenced-by-count":2,"title":["Rhythm Modeling for Voice Conversion"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9207-6309","authenticated-orcid":false,"given":"Benjamin","family":"van Niekerk","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0677-415X","authenticated-orcid":false,"given":"Marc-Andr\u00e9","family":"Carbonneau","sequence":"additional","affiliation":[{"name":"Ubisoft La Forge, Montréal, QC, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2980-3475","authenticated-orcid":false,"given":"Herman","family":"Kamper","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/002383098703000403"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1006\/jpho.2001.0138"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.lingua.2012.01.004"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/S0954394501132023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1075\/eww.27.3.06tho"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1788"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362110"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683282"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282288"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3156757"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2203"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076867"},{"key":"ref14","first-page":"8650","article-title":"Global rhythm style transfer without text transcriptions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10740"},{"article-title":"Speaking style conversion with discrete self-supervised units","year":"2022","author":"Maimon","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref19","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Oord","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1693"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-50"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.2.4.538"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.675422"},{"volume-title":"Essentials of Linguistics","year":"2018","author":"Anderson","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1994.1005"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/S0885-2308(86)80009-2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2005.845598"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","year":"2017","author":"Veaux","key":"ref30"},{"key":"ref31","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kong","year":"2020"},{"article-title":"The LJ speech dataset","year":"2017","author":"Ito","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref34","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-15"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbef.2017.12.004"},{"journal-title":"Subjective Evaluation of Speech Quality with a Crowdsourcing Approach","year":"2018","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-1331"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/vcc_bc.2020"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/10036333\/10246359.pdf?arnumber=10246359","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T23:15:06Z","timestamp":1710371706000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10246359\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/lsp.2023.3313515","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2023]]}}}