{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:08:33Z","timestamp":1776884913826,"version":"3.51.2"},"reference-count":33,"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\/501100020785","name":"Shenzhen Research Institute of Big Data","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020785","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\/icassp48485.2024.10445996","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10601-10605","source":"Crossref","is-referenced-by-count":16,"title":["Hierarchical Emotion Prediction and Control in Text-to-Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Sho","family":"Inoue","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen),School of Data Science,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Speech Lab of DAMO Academy,Alibaba Group,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen),School of Data Science,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2001-150"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3250266"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2018.3620963"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-90-481-3129-7"},{"key":"ref5","article-title":"Emotion modelling for speech generation","author":"KUN","year":"2022"},{"key":"ref6","article-title":"A survey on neural speech synthesis","author":"Tan","year":"2021"},{"key":"ref7","first-page":"515","article-title":"Pragmatics and intonation","author":"Hirschberg","year":"2004","journal-title":"The handbook of pragmatics"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1093\/scan\/nst124"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3175578"},{"key":"ref10","first-page":"1","article-title":"Speech synthesis with mixed emotions","author":"Zhou","year":"2022","journal-title":"IEEE Transactions on Affective Computing"},{"key":"ref11","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"Wang","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126281"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003829"},{"key":"ref14","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"ref15","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-621"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref18","article-title":"Mixture density network for phone-level prosody modelling in speech synthesis","author":"Du","year":"2021","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11171"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10131"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11293"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145293"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref24","first-page":"1459","article-title":"opens-mile \u2013 the munich versatile and fast open-source audio feature extractor","author":"Eyben","year":"2010"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022627411411"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref27","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2017"},{"key":"ref29","article-title":"The blizzard challenge 2013","author":"King","year":"2014"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref32","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"Kong","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1023\/A:1023237014909"}],"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\/10445996.pdf?arnumber=10445996","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:00:52Z","timestamp":1722574852000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445996\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10445996","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}