{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:06:45Z","timestamp":1776881205432,"version":"3.51.2"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3366707","type":"journal-article","created":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T19:17:40Z","timestamp":1708111060000},"page":"31409-31421","source":"Crossref","is-referenced-by-count":8,"title":["Fast Neural Speech Waveform Generative Models With Fully-Connected Layer-Based Upsampling"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8553-9317","authenticated-orcid":false,"given":"Haruki","family":"Yamashita","sequence":"first","affiliation":[{"name":"Graduate School of System Informatics, Kobe University, Kobe, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9913-4647","authenticated-orcid":false,"given":"Takuma","family":"Okamoto","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9808-0250","authenticated-orcid":false,"given":"Ryoichi","family":"Takashima","sequence":"additional","affiliation":[{"name":"Graduate School of System Informatics, Kobe University, Kobe, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2961-2821","authenticated-orcid":false,"given":"Yamato","family":"Ohtani","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5005-7679","authenticated-orcid":false,"given":"Tetsuya","family":"Takiguchi","sequence":"additional","affiliation":[{"name":"Graduate School of System Informatics, Kobe University, Kobe, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8146-1279","authenticated-orcid":false,"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0914-5092","authenticated-orcid":false,"given":"Hisashi","family":"Kawai","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-314"},{"key":"ref3","first-page":"1","article-title":"End-to-end adversarial text-to-speech","volume-title":"Proc. ICLR","author":"Donahue"},{"key":"ref4","first-page":"1","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413851"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-831"},{"key":"ref7","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10294"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095431"},{"key":"ref10","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.","volume":"33","author":"Kong"},{"key":"ref11","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kim"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref14","first-page":"2415","article-title":"Efficient neural audio synthesis","volume-title":"Proc. ICML","author":"Kalchbrenner"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2968"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1156"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1463"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3089565"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1984"},{"key":"ref21","first-page":"3915","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","volume":"80","author":"van den Oord"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref24","first-page":"1","article-title":"WaveGrad: Estimating gradients for waveform generation","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref25","first-page":"1","article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. ICLR","author":"Kong"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415087"},{"key":"ref27","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. NeurIPS","author":"Kumar"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383551"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022496"},{"key":"ref31","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"Proc. ICML","author":"Casanova"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3272470"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096220"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095102"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097255"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096442"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096250"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1121\/1.4919349"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095298"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096480"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3275032"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3164361"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1121\/10.0016896"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-845"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1016"},{"key":"ref48","first-page":"1","article-title":"Chunked autoregressive GAN for conditional waveform synthesis","volume-title":"Proc. ICLR","author":"Morrison"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096288"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688194"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746713"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11152"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095296"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/5.52200"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/78.258122"},{"key":"ref56","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proc. 32nd Int. Conf. Mach. Learn. (PMLR)","author":"Rezende"},{"key":"ref57","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747707"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1250\/ast.41.761"},{"key":"ref62","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. NIPS","author":"Paszke"},{"key":"ref63","article-title":"ESPnet2-TTS: Extending the edge of TTS research","author":"Hayashi","year":"2021","journal-title":"arXiv:2110.07840"},{"key":"ref64","volume-title":"Methods for Subjective Determination of Transmission Quality","year":"1996"},{"key":"ref65","volume-title":"The LJ Speech Dataset","author":"Ito","year":"2017"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1599"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10438439.pdf?arnumber=10438439","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T01:10:02Z","timestamp":1709860202000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10438439\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3366707","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}