{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,4]],"date-time":"2026-01-04T10:36:58Z","timestamp":1767523018530,"version":"3.37.3"},"reference-count":35,"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":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","doi-asserted-by":"publisher","award":["JP21H05054","JP21H03467"],"award-info":[{"award-number":["JP21H05054","JP21H03467"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3251657","type":"journal-article","created":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T18:25:46Z","timestamp":1677781546000},"page":"22355-22363","source":"Crossref","is-referenced-by-count":2,"title":["Japanese Neural Incremental Text-to-Speech Synthesis Framework With an Accent Phrase Input"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8250-6088","authenticated-orcid":false,"given":"Tomoya","family":"Yanagita","sequence":"first","affiliation":[{"name":"Nara Institute of Science and Technology, Ikoma, Nara, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5509-8963","authenticated-orcid":false,"given":"Sakriani","family":"Sakti","sequence":"additional","affiliation":[{"name":"Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6956-3803","authenticated-orcid":false,"given":"Satoshi","family":"Nakamura","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology, Ikoma, Nara, Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860774"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF01068102"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref5","first-page":"1","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume-title":"Proc. NeurIPS","volume":"32","author":"Ren"},{"key":"ref6","first-page":"1","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054484"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WSS.2002.1224415"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref12","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Oord"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref14","first-page":"2410","article-title":"Efficient neural audio synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kalchbrenner"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-152"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-304"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-165"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1561"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-33"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.346"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2103"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1822"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-275"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3073869"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-177"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682353"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-30"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2020EDP7104"},{"key":"ref31","article-title":"JSUT corpus: Free large-scale Japanese speech corpus for end-to-end speech synthesis","author":"Sonobe","year":"2017","journal-title":"arXiv:1711.00354"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462020"},{"key":"ref33","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"volume-title":"Methods for Subjective Determination of Transmission Quality","year":"1996","key":"ref35"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10057419.pdf?arnumber=10057419","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T00:03:58Z","timestamp":1709424238000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10057419\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3251657","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2023]]}}}