{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:26:14Z","timestamp":1775229974036,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414975","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"5964-5968","source":"Crossref","is-referenced-by-count":11,"title":["Zero-Shot Voice Conversion with Adjusted Speaker Embeddings and Simple Acoustic Features"],"prefix":"10.1109","author":[{"given":"Zhiyuan","family":"Tan","sequence":"first","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianguo","family":"Wei","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhai","family":"Xu","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqing","family":"He","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhuan","family":"Lu","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","article-title":"CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit","author":"veaux","year":"2016","journal-title":"Centre for Speech Technology Research University of Edinburgh"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/FSKD.2007.347"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2013.6694179"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178894"},{"key":"ref12","first-page":"201","article-title":"Exemplar-based voice conversion using non-negative spectrogram deconvolution","author":"wu","year":"2013","journal-title":"ISCA Workshop on Speech Synthesis"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E97.D.1403"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref17","first-page":"1","article-title":"Voice conversion from non-parallel corpora using variational autoencoder","author":"hsu","year":"2016","journal-title":"APSIPA 2016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706604"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639647"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054734"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCI.2016.7732175"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2205241"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1066"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CompComm.2018.8780827"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-970"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"195","DOI":"10.21437\/Odyssey.2018-28","article-title":"The voice conversion challenge 2018: Promoting development of parallel and nonparallel methods","author":"lorenzo-trueba","year":"2018","journal-title":"Proc Odyssey 2018 The Speaker and Language Recognition Workshop"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.07.007"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415037"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462018"},{"key":"ref20","first-page":"287","article-title":"A KL Divergence and DNN-based Approach to Voice Conversion without Parallel Training Sentences","author":"xie","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053842"},{"key":"ref21","first-page":"5210","article-title":"AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss","author":"qian","year":"2019","journal-title":"Proc PMLR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682320"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053854"},{"key":"ref26","first-page":"4480","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"NIPS 2018 - Advances in Neural Information Processing Systems 31 (NIPS)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1325912"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414975.pdf?arnumber=9414975","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:19:23Z","timestamp":1659485963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414975\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414975","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}