{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:33:12Z","timestamp":1760661192526,"version":"build-2065373602"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62301521"],"award-info":[{"award-number":["62301521"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2308085QF200"],"award-info":[{"award-number":["2308085QF200"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lsp.2025.3598729","type":"journal-article","created":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T17:37:22Z","timestamp":1755106642000},"page":"3485-3489","source":"Crossref","is-referenced-by-count":0,"title":["Is GAN Necessary for Mel-Spectrogram-Based Neural Vocoder?"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9831-6086","authenticated-orcid":false,"given":"Hui-Peng","family":"Du","sequence":"first","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6668-022X","authenticated-orcid":false,"given":"Yang","family":"Ai","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8074-9553","authenticated-orcid":false,"given":"Rui-Chen","family":"Zheng","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8026-0702","authenticated-orcid":false,"given":"Ye-Xin","family":"Lu","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7853-5273","authenticated-orcid":false,"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"article-title":"CosyVoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","year":"2024","author":"Du","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1441"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447246"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3519881"},{"article-title":"Spectral Codecs: Spectrogram-based audio codecs for high quality speech synthesis","year":"2024","author":"Langman","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3482359"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461878"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2970241"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref12","first-page":"7706","article-title":"WaveFlow: A compact flow-based model for raw audio","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ping","year":"2020"},{"key":"ref13","first-page":"14881","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kumar","year":"2019"},{"key":"ref14","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","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3277276"},{"key":"ref16","article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746713"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447251"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1647"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413727"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-0601-3_6"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2407"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096553"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832214"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-255"},{"article-title":"Gaussian error linear units (GELUs)","year":"2016","author":"Hendrycks","key":"ref28"},{"key":"ref29","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.","author":"Ziyin","year":"2020"},{"article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","year":"2019","author":"Yamagishi","key":"ref30"},{"key":"ref31","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref32","article-title":"Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Siuzdak","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10802935\/11123758.pdf?arnumber=11123758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T17:41:48Z","timestamp":1760636508000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11123758\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/lsp.2025.3598729","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2025]]}}}