{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T16:10:26Z","timestamp":1782835826523,"version":"3.54.5"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022793","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T13:54:03Z","timestamp":1674827643000},"page":"892-899","source":"Crossref","is-referenced-by-count":6,"title":["On Granularity of Prosodic Representations in Expressive Text-to-Speech"],"prefix":"10.1109","author":[{"given":"Mikolaj","family":"Babianski","sequence":"first","affiliation":[{"name":"Amazon Text-to-Speech Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kamil","family":"Pokora","sequence":"additional","affiliation":[{"name":"Amazon Text-to-Speech Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raahil","family":"Shah","sequence":"additional","affiliation":[{"name":"Amazon Text-to-Speech Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rafal","family":"Sienkiewicz","sequence":"additional","affiliation":[{"name":"Amazon Text-to-Speech Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Korzekwa","sequence":"additional","affiliation":[{"name":"Amazon Text-to-Speech Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Viacheslav","family":"Klimkov","sequence":"additional","affiliation":[{"name":"Amazon Text-to-Speech Research"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414413"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref34","first-page":"518","article-title":"A robust algorithm for pitch tracking (rapt)","volume":"495","author":"talkin","year":"1995","journal-title":"Speech Coding and Synthesis"},{"key":"ref15","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746883"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87802-3_31"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1599"},{"key":"ref31","year":"2003"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414444"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413696"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326009"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref32","article-title":"Statistical analysis of the blizzard challenge 2007 listening test results","volume":"2007","author":"clark","year":"0","journal-title":"Proc Blizzard Challenge Workshop"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-2026"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref17","article-title":"Delightfultts: The microsoft speech synthesis system for blizzard challenge 2021","author":"liu","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414718"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746323"},{"key":"ref19","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"0","journal-title":"ICLRE"},{"key":"ref18","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054106"},{"key":"ref26","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1016\/j.specom.2009.04.004","article-title":"Statistical parametric speech synthesis","volume":"51","author":"zen","year":"2009","journal-title":"Speech Communication"},{"key":"ref20","article-title":"Non-attentive tacotron: Robust and controllable neural tts synthesis including unsupervised duration modeling","author":"shen","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2176"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1972"},{"key":"ref28","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref27","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":"International Conference on Machine Learning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref8","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry-ryan","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10195"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-17"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-14"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2571"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1251"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022793.pdf?arnumber=10022793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T17:08:09Z","timestamp":1676912889000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022793\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022793","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}