{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:02:12Z","timestamp":1764403332958,"version":"3.37.3"},"reference-count":23,"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"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","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\/icassp48485.2024.10446506","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10706-10710","source":"Crossref","is-referenced-by-count":6,"title":["Concss: Contrastive-based Context Comprehension for Dialogue-Appropriate Prosody in Conversational Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Yayue","family":"Deng","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinlong","family":"Xue","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukang","family":"Jia","sequence":"additional","affiliation":[{"name":"Perfect World Co., Ltd,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qifei","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yichen","family":"Han","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengping","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingming","family":"Gao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dengfeng","family":"Ke","sequence":"additional","affiliation":[{"name":"Beijing Language and Culture University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ya","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Naturalspeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers","year":"2023","author":"Shen","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref3","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"ICLR","author":"Ren","year":"2021"},{"key":"ref4","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"ICML","author":"Kim","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1008662107"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1903402116"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-36"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11171"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-119"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095751"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096905"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383460"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-403"},{"key":"ref14","article-title":"Fctalker: Fine and coarse grained context modeling for expressive conversational speech synthesis","author":"Hu","year":"2022","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747837"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547831"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref18","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","volume-title":"NAACL-HLT (1)","author":"Devlin","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746883"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"11","key":"ref21","article-title":"Visualizing data using t-sne","volume":"9","author":"der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","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\/10446506.pdf?arnumber=10446506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:19:34Z","timestamp":1722575974000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446506\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446506","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}