{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T20:18:06Z","timestamp":1779135486642,"version":"3.51.4"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100018625","name":"Industry-University Cooperation Project through Shanghai\u2019s Science and Technology Innovation Action Plan","doi-asserted-by":"publisher","award":["2242300201006"],"award-info":[{"award-number":["2242300201006"]}],"id":[{"id":"10.13039\/501100018625","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Industry-University Cooperation and Collaborative Education Project of the Ministry of Education","award":["231003221260825"],"award-info":[{"award-number":["231003221260825"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3691952","type":"journal-article","created":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T19:47:35Z","timestamp":1778528855000},"page":"71295-71308","source":"Crossref","is-referenced-by-count":0,"title":["A Multi-Level Expressive Voice Cloning Method Based on Adaptive Grouped Code Modeling"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0222-7717","authenticated-orcid":false,"given":"Yan","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Design and Art, Shanghai Dianji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0528-883X","authenticated-orcid":false,"given":"Rui","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Design and Art, Shanghai Dianji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Chen","sequence":"additional","affiliation":[{"name":"Tongxing Tech, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/access.2025.3603099"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3110137"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2018.8461368"},{"key":"ref5","article-title":"CosyVoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","author":"Du","year":"2024","journal-title":"arXiv:2407.05407"},{"key":"ref6","article-title":"VALL-E 2: Neural codec language models are human parity zero-shot text-to-speech synthesizers","author":"Chen","year":"2024","journal-title":"arXiv:2406.05370"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3049294"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.2542"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.2992934"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-026-05196-7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/app13148049"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12040820"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2022.108534"},{"key":"ref14","article-title":"CosyVoice 2: Scalable streaming speech synthesis with large language models","author":"Du","year":"2024","journal-title":"arXiv:2412.10117"},{"key":"ref15","article-title":"MaskGCT: Zero-shot text-to-speech with masked generative codec transformer","author":"Wang","year":"2024","journal-title":"arXiv:2409.00750"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3519870"},{"key":"ref17","article-title":"DiffGAN-TTS: High-fidelity and efficient text-to-speech with denoising diffusion GANs","author":"Liu","year":"2022","journal-title":"arXiv:2201.11972"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-024-00329-7"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3144163"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.2325"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/math11143217"},{"key":"ref22","article-title":"Density estimation using real NVP","author":"Dinh","year":"2016","journal-title":"arXiv:1605.08803"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-834"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10195"},{"key":"ref25","article-title":"HALL-E: Hierarchical neural codec language model for minute-long zero-shot text-to-speech synthesis","author":"Nishimura","year":"2024","journal-title":"arXiv:2410.04380"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2477"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-465"},{"key":"ref28","article-title":"RALL-E: Robust codec language modeling with chain-of-thought prompting for text-to-speech synthesis","author":"Xin","year":"2024","journal-title":"arXiv:2404.03204"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2024-208"},{"key":"ref30","article-title":"OpenVoice: Versatile instant voice cloning","author":"Qin","year":"2023","journal-title":"arXiv:2312.01479"},{"key":"ref31","article-title":"EmergentTTS-Eval: Evaluating TTS models on complex prosodic, expressiveness, and linguistic challenges using model-as-a-judge","author":"Manku","year":"2025","journal-title":"arXiv:2505.23009"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2019.2953810"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1121\/10.0003557"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-022-00260-9"},{"key":"ref35","article-title":"PromptTTS 2: Describing and generating voices with text prompt","author":"Leng","year":"2023","journal-title":"arXiv:2309.02285"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref37","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. 12th Int. Conf. Lang. Resour. Eval. (LREC)","author":"Ardila"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.2465"},{"key":"ref39","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv:2006.04558"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/access.2023.3317360"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853678"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0446-1"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11513847.pdf?arnumber=11513847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T19:48:02Z","timestamp":1779133682000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11513847\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3691952","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}