{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:33:35Z","timestamp":1780418015952,"version":"3.54.1"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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\/501100011222","name":"National Laboratory of Pattern Recognition","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011222","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096905","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":13,"title":["M<sup>2<\/sup>-CTTS: End-to-End Multi-Scale Multi-Modal Conversational Text-to-Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Jinlong","family":"Xue","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yayue","family":"Deng","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengping","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ya","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingming","family":"Gao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,NLPR, Institute of Automation,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianqing","family":"Sun","sequence":"additional","affiliation":[{"name":"Unisound AI Technology Co., Ltd,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaen","family":"Liang","sequence":"additional","affiliation":[{"name":"Unisound AI Technology Co., Ltd,Beijing,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":"international conference on machine learning","author":"Skerry-Ryan"},{"key":"ref2","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020"},{"key":"ref3","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref5","first-page":"7748","article-title":"Meta-stylespeech: Multi-speaker adaptive text-to-speech generation","volume-title":"International Conference on Machine Learning","author":"Min"},{"key":"ref6","article-title":"Cross-speaker emotion transfer based on speaker condition layer normalization and semi-supervised training in text-to-speech","author":"Wu","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145293"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747837"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383460"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-412"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2021.104619"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095751"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref14","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref16","article-title":"Dailydialog: A manually labelled multi-turn dialogue dataset","author":"Li","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747707"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref19","first-page":"17022","article-title":"Hifigan: 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":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096905.pdf?arnumber=10096905","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T22:54:16Z","timestamp":1709247256000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096905\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096905","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}