{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T14:30:33Z","timestamp":1780756233993,"version":"3.54.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"JST, CREST","award":["JPMJCR19A3"],"award-info":[{"award-number":["JPMJCR19A3"]}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP21H05054"],"award-info":[{"award-number":["JP21H05054"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3313410","type":"journal-article","created":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T19:11:16Z","timestamp":1694459476000},"page":"3717-3729","source":"Crossref","is-referenced-by-count":8,"title":["High-Fidelity and Pitch-Controllable Neural Vocoder Based on Unified Source-Filter Networks"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9686-4783","authenticated-orcid":false,"given":"Reo","family":"Yoneyama","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4390-1354","authenticated-orcid":false,"given":"Yi-Chiao","family":"Wu","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Nagoya University, Nagoya, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8146-1279","authenticated-orcid":false,"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Information Technology Center, Nagoya University, Nagoya, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.1916020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1966.4841"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164910"},{"key":"ref6","article-title":"WaveNet: A generative model for raw audio","volume-title":"Proc. 9th ISCA Speech Synth. Workshop","author":"Oord","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref8","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":"ref9","article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kong","year":"2021"},{"key":"ref10","article-title":"WaveGrad: Estimating gradients for waveform generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413605"},{"key":"ref12","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kong","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414401"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-976"},{"key":"ref15","article-title":"Chunked autoregressive GAN for conditional waveform synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Morrison","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1288"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683271"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2008"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682298"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3188"},{"key":"ref23","article-title":"Neural pitch-shifting and time-stretching with controllable LPCNet","author":"Morrison","year":"2021"},{"key":"ref24","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Goodfellow","year":"2014"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1070"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3051765"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-517"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11130"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref30","first-page":"2415","article-title":"Efficient neural audio synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kalchbrenner","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.58"},{"key":"ref32","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Oord","year":"2018"},{"key":"ref33","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ping","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1965"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref36","first-page":"14910","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kumar","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413369"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383551"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1238"},{"key":"ref40","article-title":"High fidelity speech synthesis with adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bikowski","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1232"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3061245"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2956145"},{"key":"ref45","first-page":"C17","article-title":"Analysis synthesis telephony based on the maximum likelihood method","volume-title":"Proc. 6th Int. Congr. Acoust.","author":"Itakura","year":"1968"},{"key":"ref46","first-page":"360","article-title":"Predictive coding of speech signals","volume-title":"Proc. Speech Commun. Process.","author":"Atal","year":"1967"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1982.1163960"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/89.397089"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.09.003"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/89.890068"},{"key":"ref51","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref52","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref53","article-title":"On the variance of the adaptive learning rate and beyond","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2020"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-68"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.09.001"},{"key":"ref56","article-title":"librosa\/librosa: 0.9.2","author":"McFee","year":"2022"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10246854.pdf?arnumber=10246854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T01:18:21Z","timestamp":1705022301000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10246854\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3313410","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}