{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:54:59Z","timestamp":1753602899905,"version":"3.32.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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","award":["62206136"],"award-info":[{"award-number":["62206136"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800061","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"299-303","source":"Crossref","is-referenced-by-count":1,"title":["FCTalker: Fine and Coarse Grained Context Modeling for Expressive Conversational Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Yifan","family":"Hu","sequence":"first","affiliation":[{"name":"Inner Mongolia University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Liu","sequence":"additional","affiliation":[{"name":"Inner Mongolia University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanglai","family":"Gao","sequence":"additional","affiliation":[{"name":"Inner Mongolia University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383460"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-412"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-02176-3"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1145\/3534678.3539209","article-title":"Duplex conversation: Towards human-like interaction in spoken dialogue systems","volume-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"Lin"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref7","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/s0167-6393(96)00071-4"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2008-146"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-190"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-679"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-259"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747123"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3172699"},{"key":"ref18","article-title":"Modeling long context for task-onenteo dialogue state generation","author":"Quan","year":"2020","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6322"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1055"},{"key":"ref21","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of NAACL-HLT","author":"Devlin","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1095"},{"key":"ref23","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":"ref24","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","volume-title":"International Conference on Learning Representations","author":"Ping","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747707"},{"key":"ref26","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.66"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547831"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095751"},{"key":"ref31","article-title":"Dailydialog: A manually labelled multi-turn dialogue dataset","author":"Li","year":"2017","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Multi-domain task-completion dialog challenge","volume-title":"Dialog System Technology Challenges 8","author":"Lee","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6394"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3016564"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0446-1"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2024,11,7]]},"location":"Beijing, China","end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800061.pdf?arnumber=10800061","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:29:23Z","timestamp":1735021763000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800061\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800061","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}