{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:03:14Z","timestamp":1783526594187,"version":"3.55.0"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Guangdong Provincial Key Laboratory of Big Data Computing"},{"DOI":"10.13039\/100022813","name":"Chinese University of Hong Kong, Shenzhen","doi-asserted-by":"publisher","award":["B10120210117-KP02"],"award-info":[{"award-number":["B10120210117-KP02"]}],"id":[{"id":"10.13039\/100022813","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Natural Science Foundation Key Project","award":["JCYJ20220818103001002"],"award-info":[{"award-number":["JCYJ20220818103001002"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271432"],"award-info":[{"award-number":["62271432"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["ZDSYS20230626091302006"],"award-info":[{"award-number":["ZDSYS20230626091302006"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3439996","type":"journal-article","created":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T19:01:15Z","timestamp":1724871675000},"page":"4146-4156","source":"Crossref","is-referenced-by-count":8,"title":["RefXVC: Cross-Lingual Voice Conversion With Enhanced Reference Leveraging"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7945-0535","authenticated-orcid":false,"given":"Mingyang","family":"Zhang","sequence":"first","affiliation":[{"name":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Ren","sequence":"additional","affiliation":[{"name":"Speech & Audio team, ByteDance AI Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4449-1174","authenticated-orcid":false,"given":"Chen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Speech & Audio team, ByteDance AI Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Yin","sequence":"additional","affiliation":[{"name":"Speech & Audio team, ByteDance AI Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-9401","authenticated-orcid":false,"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115676"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-488"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-581"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683746"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038663"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref7","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3271107"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3125142"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-1770.1992.tb01043.x"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955858"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-63"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3232"},{"issue":"21","key":"ref15","doi-asserted-by":"crossref","DOI":"10.3390\/app132111988","article-title":"Any-to-one non-parallel voice conversion system using an autoregressive conversion model and LPCNet vocoder","volume":"13","author":"Ezzine","year":"2023","journal-title":"Appl. Sci."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003939"},{"key":"ref19","first-page":"5210","article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian","year":"2019"},{"key":"ref20","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202,","author":"Radford","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389651"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372889"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref25","article-title":"Self-supervised learning of motion capture","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"30","author":"Tung","year":"2017"},{"key":"ref26","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lan","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref29","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref30","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746430"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414460"},{"key":"ref36","article-title":"A fine-tuned wav2vec 2.0\/HuBERT benchmark for speech emotion recognition, speaker verification and spoken language understanding","author":"Wang","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.63"},{"key":"ref38","article-title":"Bag of tricks for unsupervised text-to-speech","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Ren","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2650"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414257"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053854"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2663"},{"key":"ref44","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"31","author":"Jia","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066047"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1033"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2020.2977678"},{"key":"ref48","article-title":"Deep Voice 3: 2000-Speaker neural text-to-speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ping","year":"2018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-1420"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/AIVR52153.2021.00067"},{"key":"ref51","article-title":"NANSY++: Unified voice synthesis with neural analysis and synthesis","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Choi","year":"2022"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1789"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054636"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2679"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326656"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3027619"},{"key":"ref57","article-title":"Attention is all you need","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani","year":"2017,"},{"key":"ref58","first-page":"3188","article-title":"Multi-reference training with pseudo-references for neural translation and text generation","volume-title":"Proc. 2018 Conf. Empirical Methods Natural Lang. Process.","author":"Zheng","year":"2018"},{"key":"ref59","article-title":"Multi-reference tacotron by intercross training for style disentangling, transfer and control in speech synthesis","author":"Bian","year":"2019"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2985"},{"key":"ref61","article-title":"MR-SVS: Singing voice synthesis with multi-reference encoder","author":"Wang","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404847"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054734"},{"key":"ref65","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"Veaux","year":"2017"},{"key":"ref66","article-title":"The M-AILabs speech dataset","author":"Solak","year":"2021"},{"key":"ref67","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Kong","year":"2020"},{"issue":"11","key":"ref68","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-817"},{"key":"ref71","first-page":"7748","article-title":"Meta-StyleSpeech: Multi-speaker adaptive text-to-speech generation","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Min","year":"2021"},{"key":"ref72","article-title":"The evaluation of comprehensibility in non-native English speakers","author":"Javernick","year":"2021"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1075\/cilt.272.05car"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10654508.pdf?arnumber=10654508","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T17:29:49Z","timestamp":1727112589000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10654508\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3439996","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}