{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T16:04:47Z","timestamp":1781366687115,"version":"3.54.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10445879","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10301-10305","source":"Crossref","is-referenced-by-count":19,"title":["TextrolSpeech: A Text Style Control Speech Corpus with Codec Language Text-to-Speech Models"],"prefix":"10.1109","author":[{"given":"Shengpeng","family":"Ji","sequence":"first","affiliation":[{"name":"Zhejiang University,Huawei Cloud"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jialong","family":"Zuo","sequence":"additional","affiliation":[{"name":"Zhejiang University,Huawei Cloud"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minghui","family":"Fang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Huawei Cloud"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyue","family":"Jiang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Huawei Cloud"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feiyang","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University,Huawei Cloud"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Duan","sequence":"additional","affiliation":[{"name":"Zhejiang University,Huawei Cloud"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baoxing","family":"Huai","sequence":"additional","affiliation":[{"name":"Zhejiang University,Huawei Cloud"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University,Huawei Cloud"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020"},{"key":"ref2","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref3","article-title":"Mega-tts: Zero-shot text-to-speech at scale with intrinsic inductive bias","author":"Jiang","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-645"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1361"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-866"},{"key":"ref7","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"international conference on machine learning","author":"Skerry-Ryan"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref9","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1779"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3402088"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.7488\/ds\/2645"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref15","article-title":"Toronto emotional speech set (tess)-younger talker_happy","author":"Dupuis","year":"2010"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1044\/2019_JSLHR-S-19-0144"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3411763.3451760"},{"key":"ref20","article-title":"Clipcap: Clip prefix for image captioning","author":"Mokady","year":"2021"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10445879.pdf?arnumber=10445879","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:57:58Z","timestamp":1722574678000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445879\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10445879","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}