{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:38:38Z","timestamp":1776886718807,"version":"3.51.2"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389651","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T13:38:40Z","timestamp":1705671520000},"page":"1-8","source":"Crossref","is-referenced-by-count":15,"title":["Using Joint Training Speaker Encoder With Consistency Loss to Achieve Cross-Lingual Voice Conversion and Expressive Voice Conversion"],"prefix":"10.1109","author":[{"given":"Houjian","family":"Guo","sequence":"first","affiliation":[{"name":"Guardian Robot Project, RIKEN,Interactive Robot Research Team,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaoran","family":"Liu","sequence":"additional","affiliation":[{"name":"Guardian Robot Project, RIKEN,Interactive Robot Research Team,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlos Toshinori","family":"Ishi","sequence":"additional","affiliation":[{"name":"Guardian Robot Project, RIKEN,Interactive Robot Research Team,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Ishiguro","sequence":"additional","affiliation":[{"name":"Osaka University,Graduate School of Engineering Science,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362120"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683746"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687906"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688219"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3156757"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076867"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2020.3038524"},{"key":"ref11","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref12","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv preprint arXiv:2006.04558"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094850"},{"key":"ref18","article-title":"Quickvc: Many-to-any voice conversion using inverse short-time fourier transform for faster conversion","author":"Guo","year":"2023","journal-title":"arXiv preprint arXiv:2302.08296"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747020"},{"key":"ref20","first-page":"2709","article-title":"Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone","volume-title":"International Conference on Machine Learning","author":"Casanova"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-687"},{"key":"ref22","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022","journal-title":"arXiv preprint arXiv:2212.04356"},{"key":"ref23","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2301.02111"},{"key":"ref24","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-755"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref27","article-title":"Jvs corpus: free japanese multi-speaker voice corpus","author":"Takamichi","year":"2019","journal-title":"arXiv preprint arXiv:1908.06248"},{"key":"ref28","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019","journal-title":"University of Edinburgh. The Centre for Speech Technology Research (CSTR)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2018.8693044"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00003"},{"key":"ref32","article-title":"The emotional voices database: Towards controlling the emotion dimension in voice generation systems","author":"Adigwe","year":"2018","journal-title":"arXiv preprint arXiv:1806.09514"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10249"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389651.pdf?arnumber=10389651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T11:42:25Z","timestamp":1706010145000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389651\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389651","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}