{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,4]],"date-time":"2026-01-04T10:36:30Z","timestamp":1767522990250,"version":"3.37.3"},"reference-count":26,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"JSPS KAKENHI","award":["17H06101","19H01116","MIC\/SCOPE #182103104"],"award-info":[{"award-number":["17H06101","19H01116","MIC\/SCOPE #182103104"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/lsp.2021.3073869","type":"journal-article","created":{"date-parts":[[2021,4,16]],"date-time":"2021-04-16T19:54:01Z","timestamp":1618602841000},"page":"857-861","source":"Crossref","is-referenced-by-count":14,"title":["Incremental Text-to-Speech Synthesis Using Pseudo Lookahead With Large Pretrained Language Model"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6003-768X","authenticated-orcid":false,"given":"Takaaki","family":"Saeki","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0520-7847","authenticated-orcid":false,"given":"Shinnosuke","family":"Takamichi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0876-5617","authenticated-orcid":false,"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-33"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2103"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1822"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref16","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"0","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1082"},{"article-title":"The LJ Speech Dataset","year":"2017","author":"ito","key":"ref18"},{"article-title":"Gentle: A Robust Yet Lenient Forced Aligner Built on Kaldi","year":"2017","author":"ochshorn","key":"ref19"},{"key":"ref4","first-page":"3886","article-title":"Incremental text-to-speech synthesis with prefix-to-prefix framework","author":"ma","year":"0","journal-title":"Proc Empirical Methods Natural Lang Process Online"},{"article-title":"Language models are unsupervised multitask learners","year":"2019","author":"radford","key":"ref3"},{"article-title":"PPSpeech: Phrase based parallel end-to-end TTS system","year":"2020","author":"cong","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref7","first-page":"227","article-title":"An HMM-based speech synthesis system applied to english","author":"tokuda","year":"0","journal-title":"Proc IEEE Workshop Speech Synthesis"},{"article-title":"Simultaneous speech-to-speech translation system with neural incremental ASR MT, and TTS","year":"2020","author":"sudoh","key":"ref2"},{"key":"ref9","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref1","first-page":"437","article-title":"Real-time incremental speech-to-speech translation of dialogs","author":"bangalore","year":"0","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguist Human Lang Technol"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref21","first-page":"707","article-title":"Binary codes capable of correcting deletions, insertions and reversals","volume":"10","author":"levenshtein","year":"1966","journal-title":"Sov Phys Doklady"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/1745691610393980"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0446-1"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/9325893\/09406329.pdf?arnumber=9406329","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:58:14Z","timestamp":1639771094000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9406329\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/lsp.2021.3073869","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2021]]}}}