{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T16:28:09Z","timestamp":1782836889274,"version":"3.54.5"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52371363"],"award-info":[{"award-number":["52371363"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301109"],"award-info":[{"award-number":["62301109"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2020M680932"],"award-info":[{"award-number":["2020M680932"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Consumer Electron."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tce.2024.3412053","type":"journal-article","created":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T18:25:46Z","timestamp":1718130346000},"page":"6054-6063","source":"Crossref","is-referenced-by-count":4,"title":["FGP-GAN: Fine-Grained Perception Integrated Generative Adversarial Network for Expressive Mandarin Singing Voice Synthesis"],"prefix":"10.1109","volume":"70","author":[{"given":"Xin","family":"Liu","sequence":"first","affiliation":[{"name":"Information Science and Technology College, Dalian Maritime University, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8445-7398","authenticated-orcid":false,"given":"Weiwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Information Science and Technology College, Dalian Maritime University, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaohui","family":"Zheng","sequence":"additional","affiliation":[{"name":"Information Science and Technology College, Dalian Maritime University, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1327-6105","authenticated-orcid":false,"given":"Mingyang","family":"Pan","sequence":"additional","affiliation":[{"name":"Navigation College, Dalian Maritime University, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian Minzu University, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/AIVR52153.2021.00067"},{"key":"ref2","article-title":"A comprehensive survey on deep music generation: Multi-level representations, algorithms, evaluations, and future directions","author":"Ji","year":"2020","journal-title":"arXiv:2011.06801"},{"key":"ref3","first-page":"733","article-title":"Ethics of singing voice synthesis: Perceptions of users and developers","volume-title":"Proc. Int. Soc. Music Inf. Retr. Conf.","author":"Lee"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/9747342"},{"key":"ref5","first-page":"1","article-title":"Concatenation-based MIDI-to-singing voice synthesis","volume-title":"Proc. Audio Eng. Soc. Conv.","author":"Macon"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-584"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1575"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3104165"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053811"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1410"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-239"},{"key":"ref13","first-page":"7586","article-title":"Non-autoregressive neural text-to-speech","volume-title":"Proc. Int. Conf. Machine Learn.","author":"Peng"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.564"},{"key":"ref15","article-title":"Xiaoicesing 2: A high-fidelity singing voice synthesizer based on generative adversarial network","author":"Wang","year":"2022","journal-title":"arXiv:2210.14666"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3285626"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3329574"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414348"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3294712"},{"key":"ref20","article-title":"HiFiSinger: Towards high-fidelity neural singing voice synthesis","author":"Chen","year":"2020","journal-title":"arXiv:2009.01776"},{"key":"ref21","article-title":"TF-GAN: Time and frequency domain based generative adversarial network for high-fidelity speech synthesis","author":"Tian","year":"2020","journal-title":"arXiv:2011.12206"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383551"},{"key":"ref23","article-title":"HiFi-GAN: Generative adversarial net-works for efficient and high fidelity speech synthesis","author":"Kong","year":"2020","journal-title":"arXiv:2010.05646"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1238"},{"key":"ref25","first-page":"910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref26","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arjovsky"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13626"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076369"},{"key":"ref29","article-title":"FastSpeech2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv:2006.04558"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688029"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref33","first-page":"1583","article-title":"Neural networks fail to learn periodic functions and how to fix it","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ziyin"},{"key":"ref34","article-title":"BigVGAN: A universal neural vocoder with large-scale training","author":"Lee","year":"2022","journal-title":"arXiv:2206.04658"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-48"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3328092"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87802-3_37"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/APCCAS.2004.1413079"},{"key":"ref43","first-page":"347","article-title":"A machine learning approach to violin vibrato modelling in audio performances and a didactic application for mobile devices","volume-title":"Proc. 15th Sound Music Comput. Conf. (SMC)","author":"Lionello"},{"key":"ref44","first-page":"3171","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref45","first-page":"6588","article-title":"FastPitch: Parallel text-to-speech with pitch prediction","volume-title":"Proc. Int. Conf. Acoust., Speech Signal Process.","author":"\u0141a\u0144cucki"}],"container-title":["IEEE Transactions on Consumer Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/30\/10798997\/10552819.pdf?arnumber=10552819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T19:19:40Z","timestamp":1734376780000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10552819\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":45,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tce.2024.3412053","relation":{},"ISSN":["0098-3063","1558-4127"],"issn-type":[{"value":"0098-3063","type":"print"},{"value":"1558-4127","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}