{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T15:20:54Z","timestamp":1767626454441,"version":"3.28.0"},"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\/icassp49357.2023.10096247","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":10,"title":["Improving Speech Prosody of Audiobook Text-To-Speech Synthesis with Acoustic and Textual Contexts"],"prefix":"10.1109","author":[{"given":"Detai","family":"Xin","sequence":"first","affiliation":[{"name":"Rakuten Group, Inc,Japan"}]},{"given":"Sharath","family":"Adavanne","sequence":"additional","affiliation":[{"name":"Rakuten Group, Inc,Japan"}]},{"given":"Federico","family":"Ang","sequence":"additional","affiliation":[{"name":"Rakuten Group, Inc,Japan"}]},{"given":"Ashish","family":"Kulkarni","sequence":"additional","affiliation":[{"name":"Rakuten Group, Inc,Japan"}]},{"given":"Shinnosuke","family":"Takamichi","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Graduate School of Information Science and Technology,Japan"}]},{"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[{"name":"The University of Tokyo,Graduate School of Information Science and Technology,Japan"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415078"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"devlin","key":"ref12"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746238"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-638"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-37"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414102"},{"key":"ref2","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"ren","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-379"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.593"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3202126"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2001-396"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-444"},{"key":"ref26","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"Proc ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref20","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref22","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"NIPS 2014 Deep Learning Workshop"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"article-title":"Deep speaker: an end-to-end neural speaker embedding system","year":"2017","author":"li","key":"ref28"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref27"},{"article-title":"Using previous acoustic context to improve text-to-speech synthesis","year":"2020","author":"oplustil-gallegos","key":"ref8"},{"key":"ref7","article-title":"The blizzard challenge 2018","author":"simon","year":"2018","journal-title":"Proc Blizzard Challenge Workshop"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-36"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511816338"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","year":"2020","author":"ren","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/23273798.2014.963130"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.02.005"}],"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\/10096247.pdf?arnumber=10096247","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:01:58Z","timestamp":1700506918000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096247\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096247","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}