{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T11:24:07Z","timestamp":1787916247362,"version":"build-2784847793"},"reference-count":13,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683501","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"5911-5915","source":"Crossref","is-referenced-by-count":82,"title":["Robust and Fine-grained Prosody Control of End-to-end Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Younggun","family":"Lee","sequence":"first","affiliation":[{"name":"Neosapience, Inc., Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taesu","family":"Kim","sequence":"additional","affiliation":[{"name":"Neosapience, Inc., Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1983.1172092"},{"key":"ref12","first-page":"2018","article-title":"An intriguing failing of convolutional neural networks and the co-ordconv solution","author":"liu","year":"0"},{"key":"ref13","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref4","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume":"80","author":"skerry-ryan","year":"2018","journal-title":"Proceedings of 35th International Conference on Machine Learning"},{"key":"ref3","first-page":"3683","article-title":"Fitting new speakers based on a short untranscribed sample","author":"nachmani","year":"2018","journal-title":"Proceedings of 35th International Conference on Machine Learning"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1109\/SLT.2018.8639682","article-title":"Predicting expressive speaking style from text in end-to-end speech synthesis","author":"stanton","year":"2018"},{"key":"ref5","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume":"80","author":"wang","year":"2018","journal-title":"Proceedings of 35th International Conference on Machine Learning"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.21437\/SpeechProsody.2002-4","article-title":"Tobi or not tobi?","author":"wightman","year":"2002","journal-title":"Speech Prosody 2002 an International Conference"},{"key":"ref7","article-title":"Tobi: a standard for labeling english prosody","author":"silverman","year":"1992","journal-title":"International Conference on Spoken Language Processing"},{"key":"ref2","first-page":"2962","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","volume":"30","author":"gibiansky","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, UK","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683501.pdf?arnumber=8683501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:37:42Z","timestamp":1755909462000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683501\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683501","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}