{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T12:23:56Z","timestamp":1764937436320,"version":"3.37.3"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003051","name":"New Energy and Industrial Technology Development Organization","doi-asserted-by":"publisher","award":["JPNP20006"],"award-info":[{"award-number":["JPNP20006"]}],"id":[{"id":"10.13039\/501100003051","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1109\/jstsp.2022.3190672","type":"journal-article","created":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T19:36:49Z","timestamp":1657741009000},"page":"1319-1328","source":"Crossref","is-referenced-by-count":11,"title":["Investigation of Japanese PnG BERT Language Model in Text-to-Speech Synthesis for Pitch Accent Language"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2130-747X","authenticated-orcid":false,"given":"Yusuke","family":"Yasuda","sequence":"first","affiliation":[{"name":"Information Technology Center, Nagoya University, Nagoya City, 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":"Information Technology Center, Nagoya University, Nagoya City, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","article-title":"Close to Human quality tts with transformer","author":"Li","year":"2018","journal-title":"arXiv:1809.08895v3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682353"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682674"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-30"},{"year":"2015","key":"ref6","article-title":"The Japanese TTS system Open JTalk"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2830"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1757"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1356"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1452"},{"article-title":"Fundamental frequency modeling for neural-network-based statistical parametric speech synthesis","year":"2018","author":"Wang","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2347"},{"key":"ref14","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"issue":"7","key":"ref15","first-page":"849","article-title":"Accentuation rules for Japanese word concatenation","volume":"66","author":"Sagisaka","year":"1983","journal-title":"IEICE Trans. Inf. Syst."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2016AWI0004"},{"key":"ref17","first-page":"148","article-title":"CRF-based statistical learning of Japanese accent sandhi for developing Japanese text-to-speech synthesis systems","volume-title":"Proc. 6th ISCA Speech Synth. Workshop","author":"Nobuaki","year":"2007"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101183"},{"key":"ref19","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"CoRR"},{"key":"ref20","first-page":"9746","article-title":"Memory efficient adaptive optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 32: Annu. Conf. Neural Inf. Process. Syst.","author":"Anil","year":"2019"},{"article-title":"Neologism dictionary based on the language resources on the web for Mecab","year":"2015","author":"Toshinori","key":"ref21"},{"key":"ref22","first-page":"1","article-title":"Operation of a word segmentation dictionary generation system called NEologd","volume-title":"Inf. Process. Soc. Japan, Special Int. Group Natural Lang. Process.","author":"Sato","year":"2016"},{"key":"ref23","first-page":"NLP2017","article-title":"Implementation of a word segmentation dictionary called mecab-ipadic-NEologd and study on how to use it effectively for information retrieval","volume-title":"Proc. 23rd Annu. Meeting Assoc. Natural Lang. Process.","author":"Sato","year":"2017"},{"key":"ref24","article-title":"JSUT corpus: Free large-scale Japanese speech corpus for end-to-end speech synthesis","author":"Sonobe","year":"2017","journal-title":"arXiv:1711.00354v1"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1004"},{"key":"ref26","first-page":"6294","article-title":"Learned in translation: Contextualized word vectors","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 30: Annu. Conf. Neural Inf. Process. Syst.","author":"McCann","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-3177"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2002-468"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177730491"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5821\/dissertation-2117-113289"},{"key":"ref36","first-page":"261","article-title":"Combining a vector space representation of linguistic context with a deep neural network for text-to-speech synthesis","volume-title":"Proc. 8th ISCA Workshop Speech Synth.","author":"Lu","year":"2013"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053390"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1118"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref40","first-page":"2","article-title":"Efficient estimation of word representations in vector space","volume-title":"Proc. 1st Int. Conf. Learn. Representations","author":"Mikolov","year":"2013"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178898"},{"key":"ref42","article-title":"Toward transfer learning for end-to-end speech synthesis from deep pre-trained language models","author":"Fang","year":"2019","journal-title":"arXiv:1906.07307v1"},{"key":"ref43","article-title":"Feature reinforcement with word embedding and parsing information in neural TTS","author":"Ming","year":"2019","journal-title":"arXiv:1901.00707v2"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054337"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414102"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-37"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1411"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1430"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413696"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683862"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4302"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-234"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413864"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/9923627\/09829304.pdf?arnumber=9829304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T06:37:28Z","timestamp":1706769448000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9829304\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":53,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2022.3190672","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"type":"print","value":"1932-4553"},{"type":"electronic","value":"1941-0484"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}