{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:22:09Z","timestamp":1740169329315,"version":"3.37.3"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3226350","type":"journal-article","created":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T20:46:29Z","timestamp":1669927589000},"page":"134029-134037","source":"Crossref","is-referenced-by-count":1,"title":["Jointly Trained Conversion Model With LPCNet for Any-to-One Voice Conversion Using Speaker-Independent Linguistic Features"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3848-244X","authenticated-orcid":false,"given":"Ivan","family":"Himawan","sequence":"first","affiliation":[{"name":"ObEN, Pasadena, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2455-9074","authenticated-orcid":false,"given":"Ruizhe","family":"Wang","sequence":"additional","affiliation":[{"name":"ObEN, Pasadena, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4316-9001","authenticated-orcid":false,"given":"Sridha","family":"Sridharan","sequence":"additional","affiliation":[{"name":"Queensland University of Technology, Brisbane, QLD, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8515-6324","authenticated-orcid":false,"given":"Clinton","family":"Fookes","sequence":"additional","affiliation":[{"name":"Queensland University of Technology, Brisbane, QLD, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.05.001"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041699"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683282"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3047262"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-63"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1514"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2960721"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1715"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/vcc_bc.2020-19"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362110"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-32"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461384"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-986"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1190"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016"},{"key":"ref24","first-page":"2410","article-title":"Efficient neural audio synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kalchbrenner"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1642"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2041"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053337"},{"key":"ref29","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"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"},{"article-title":"Chunked autoregressive GAN for conditional waveform synthesis","volume-title":"Proc. ICLR","author":"Morrison","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-552"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424246"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-912"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1316"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472718"},{"key":"ref39","first-page":"1","article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. IEEE Workshop Autom. Speech Recognit. Understand.","author":"Povey"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"volume-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","year":"2019","author":"Yamagishi","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2013.6694123"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1599"},{"key":"ref44","first-page":"4480","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jia"},{"key":"ref45","article-title":"A robust algorithm for pitch tracking (RAPT)","volume-title":"Speech Coding and Synthesis","author":"Talkin","year":"1995"},{"key":"ref46","first-page":"1","article-title":"High fidelity speech synthesis with adversarial networks","volume-title":"Proc. ICLR","author":"Binkowski"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1250\/ast.42.65"},{"key":"ref48","first-page":"12104","article-title":"Training generative adversarial networks with limited data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Karras"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09968235.pdf?arnumber=9968235","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:26:44Z","timestamp":1706758004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9968235\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3226350","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2022]]}}}