{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T05:20:49Z","timestamp":1737436849472,"version":"3.33.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832341","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"482-488","source":"Crossref","is-referenced-by-count":0,"title":["Language-Independent Prosody-Enhanced Speech Representations For Multilingual Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Chang","family":"Liu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,China"}]},{"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,China"}]},{"given":"Ya-Jun","family":"Hu","sequence":"additional","affiliation":[{"name":"iFLYTEK Co., Ltd.,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095702"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/575"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448074"},{"article-title":"Multilingual byte2speech models for scalable low-resource speech synthesis","year":"2021","author":"He","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-2133"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref8","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":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref11","first-page":"1298","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Baevski"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10797"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-489"},{"key":"ref14","first-page":"16624","article-title":"Hierspeech: Bridging the gap between text and speech by hierarchical variational inference using self-supervised representations for speech synthesis","volume":"35","author":"Lee","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3313424"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3364085"},{"key":"ref17","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Kim"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref19","first-page":"27826","article-title":"Unsupervised speech recognition","volume":"34","author":"Baevski","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.sigmorphon-1.9"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW58026.2022.00120"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2359"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1280"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023234"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2254"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref29","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"},{"article-title":"The lj speech dataset","year":"2017","author":"Ito","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2024,12,2]]},"location":"Macao","end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832341.pdf?arnumber=10832341","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:39:25Z","timestamp":1737398365000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832341\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832341","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}