{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T15:11:03Z","timestamp":1767625863601,"version":"build-2065373602"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096402","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Duration-Aware Pause Insertion Using Pre-Trained Language Model for Multi-Speaker Text-To-Speech"],"prefix":"10.1109","author":[{"given":"Dong","family":"Yang","sequence":"first","affiliation":[{"name":"The University of Tokyo,Japan"}]},{"given":"Tomoki","family":"Koriyama","sequence":"additional","affiliation":[{"name":"CyberAgent, Inc.,Japan"}]},{"given":"Yuki","family":"Saito","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}]},{"given":"Takaaki","family":"Saeki","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}]},{"given":"Detai","family":"Xin","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}]},{"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2010.5684835"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404780"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-885"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-367"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.09.004"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-419"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-591"},{"key":"ref17","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc NAACL-HLT"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-252"},{"key":"ref19","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2021","journal-title":"Proc ICLR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-384"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"338","DOI":"10.21437\/Interspeech.2014-80","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref23","first-page":"199","article-title":"A large-scale multilingual study of silent pause duration","author":"campione","year":"2002","journal-title":"Proc Speech Prosody"},{"key":"ref26","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"Proc ICLR Workshop"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref20","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","author":"kim","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"498","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal Forced Aligner: Trainable text-speech alignment using Kaldi","author":"mcauliffe","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref28","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref27","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-26"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2007-217"},{"key":"ref9","article-title":"Adaptation of prosodic phrasing models","author":"bell","year":"2006","journal-title":"Proc Speech Prosody"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-563"},{"key":"ref3","article-title":"Pause prediction from lexical and syntax information","author":"keri","year":"2007","journal-title":"Proc ICON"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-752"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-565"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096402.pdf?arnumber=10096402","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T22:10:09Z","timestamp":1729375809000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096402\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096402","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}