{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T13:13:07Z","timestamp":1780060387535,"version":"3.54.0"},"reference-count":25,"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\/icassp48485.2024.10448356","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11426-11430","source":"Crossref","is-referenced-by-count":2,"title":["Considering Temporal Connection between Turns for Conversational Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Kangdi","family":"Mei","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoci","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huipeng","family":"Du","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengyu","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Ai","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liping","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenhua","family":"Ling","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P.R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"Proc. ICML","author":"Skerry-Ryan"},{"key":"ref2","author":"Ren","year":"2020","journal-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054484"},{"key":"ref4","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref5","author":"Tan","year":"2021","journal-title":"A survey on neural speech synthesis"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-679"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2836"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.440"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10167"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00545"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383460"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-412"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747837"},{"key":"ref14","first-page":"1","article-title":"M2-CTTS: End-to-end multi-scale multi-modal conversational text-to-speech synthesis","volume-title":"Proc. ICASSP","author":"Xue"},{"key":"ref15","first-page":"69","article-title":"The Fisher corpus: A resource for the next generations of speech-to-text","volume-title":"Proc. LREC","volume":"4","author":"Cieri"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26488"},{"key":"ref17","first-page":"2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACLHLT","volume":"1","author":"Kenton"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.593"},{"key":"ref19","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NIPS","volume":"33","author":"Kong"},{"key":"ref20","author":"Baevski","year":"2019","journal-title":"vq-wav2vec: Self-supervised learning of discrete speech representations"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-37"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096247"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01033"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3277276"}],"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\/10448356.pdf?arnumber=10448356","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:52:46Z","timestamp":1722660766000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448356\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448356","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}