{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T15:47:52Z","timestamp":1771516072773,"version":"3.50.1"},"reference-count":56,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100015013","name":"Open Research Fund of the National Mobile Communications Research Laboratory, Southeast University","doi-asserted-by":"publisher","award":["2023D15"],"award-info":[{"award-number":["2023D15"]}],"id":[{"id":"10.13039\/501100015013","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ningbo Clinical Research Center for Medical Imaging","award":["2022LYKFYB01"],"award-info":[{"award-number":["2022LYKFYB01"]}]},{"DOI":"10.13039\/100007834","name":"Natural Science Foundation of Zhejiang, China","doi-asserted-by":"publisher","award":["2022LYKFYB01"],"award-info":[{"award-number":["2022LYKFYB01"]}],"id":[{"id":"10.13039\/100007834","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3561857","type":"journal-article","created":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T17:42:28Z","timestamp":1744911748000},"page":"69324-69340","source":"Crossref","is-referenced-by-count":4,"title":["DPN-GAN: Inducing Periodic Activations in Generative Adversarial Networks for High-Fidelity Audio Synthesis"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2074-8847","authenticated-orcid":false,"given":"Zeeshan","family":"Ahmad","sequence":"first","affiliation":[{"name":"Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1432-4404","authenticated-orcid":false,"given":"Shudi","family":"Bao","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5476-8662","authenticated-orcid":false,"given":"Meng","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Ningbo University of Technology, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-19361-y"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-658-40442-0_9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3359352"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3349053"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2846402"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3356232"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3227963"},{"key":"ref8","first-page":"1","article-title":"GANSynth: Adversarial neural audio synthesis","volume-title":"Proc. 7th Int. Conf. Learn. Represent.","author":"Engel"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3257381"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123261"},{"key":"ref11","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref12","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Oord"},{"key":"ref13","first-page":"125","article-title":"WaveNet: A generative model for raw audio","volume-title":"Proc. 9th ISCA Speech Synth. Workshop","author":"Oord"},{"key":"ref14","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Kong"},{"key":"ref15","first-page":"1","article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Lee"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.06.128"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref21","first-page":"195","article-title":"Deep voice: Real-time neural text-to-speech","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Ar\u0131k"},{"key":"ref22","first-page":"214","article-title":"Deep voice 3: 2000-speaker neural text-to-speech","volume-title":"Proc. 6th Int. Conf. Learn. Represent.","author":"Ping"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref24","first-page":"1","article-title":"Char2Wav: End-to-end speech synthesis","volume-title":"Proc. 5th Int. Conf. Learn. Represent. Workshop","author":"Sotelo"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref26","first-page":"1","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","volume-title":"Proc. 7th Int. Conf. Learn. Represent.","author":"Ping"},{"key":"ref27","first-page":"1","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","volume-title":"Proc. 5th Int. Conf. Learn. Represent.","author":"Mehri"},{"key":"ref28","first-page":"2410","article-title":"Efficient neural audio synthesis","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Kalchbrenner"},{"key":"ref29","first-page":"1068","article-title":"Neural audio synthesis of musical notes with WaveNet autoencoders","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Engel"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref31","first-page":"1","article-title":"NICE: Non-linear independent components estimation","volume-title":"Proc. 3rd Int. Conf. Learn. Represent.","author":"Dinh"},{"key":"ref32","first-page":"10215","article-title":"Glow: Generative flow with invertible 1\u00d71 convolutions","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Kingma"},{"key":"ref33","first-page":"1","article-title":"High fidelity speech synthesis with adversarial networks","volume-title":"Proc. 8th Int. Conf. Learn. Represent.","author":"Bi\u0144kowski"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383551"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413605"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1016"},{"key":"ref38","first-page":"1","article-title":"Chunked autoregressive GAN for conditional waveform synthesis","volume-title":"Proc. 10th Int. Conf. Learn. Represent.","author":"Morrison"},{"key":"ref39","first-page":"17450","article-title":"Efficient neural music generation","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Lam"},{"key":"ref40","first-page":"132","article-title":"Exploiting pre-trained feature networks for generative adversarial networks in audio-domain loop generation","volume-title":"Proc. 23rd ISMIR","author":"Yeh"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-845"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746675"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632757"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1137"},{"key":"ref45","first-page":"1673","article-title":"Periodic activation functions induce stationarity","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Meronen"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref47","article-title":"The LJ speech dataset","author":"Ito","year":"2017"},{"key":"ref48","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"Yamagishi","year":"2019"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2023.11.038"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953125"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414901"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446830"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10967485.pdf?arnumber=10967485","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T05:12:05Z","timestamp":1745644325000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10967485\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3561857","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}