{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:00:48Z","timestamp":1764403248703},"reference-count":24,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095840","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":9,"title":["Improving Prosody for Cross-Speaker Style Transfer by Semi-Supervised Style Extractor and Hierarchical Modeling in Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Chunyu","family":"Qiang","sequence":"first","affiliation":[{"name":"Kwai,Beijing,P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Yang","sequence":"additional","affiliation":[{"name":"Kwai,Beijing,P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Che","sequence":"additional","affiliation":[{"name":"Kwai,Beijing,P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[{"name":"Kwai,Beijing,P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaorui","family":"Wang","sequence":"additional","affiliation":[{"name":"Kwai,Beijing,P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Kwai,Beijing,P.R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747747"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746744"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980115"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10038135"},{"key":"ref14","first-page":"3331","article-title":"Chive: Varying prosody in speech synthesis with a linguistically driven dynamic hierarchical conditional variational network","author":"kenter","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3021758"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-979"},{"key":"ref22","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013","journal-title":"arXiv preprint arXiv 1312 6114"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-838"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref1","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"arXiv preprint arXiv 1703 10593"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413934"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1407"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.005"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref7","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref9","article-title":"Semi-supervised generative modeling for controllable speech synthesis","author":"habib","year":"2019","journal-title":"arXiv preprint arXiv 1910 01500"},{"key":"ref4","article-title":"Cross-speaker emotion transfer based on speaker condition layer normalization and semi-supervised training in text-to-speech","author":"wu","year":"2021","journal-title":"arXiv preprint arXiv 2110 07058"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414718"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3164181"},{"key":"ref5","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry-ryan","year":"2018","journal-title":"Int Conference on Machine Learning"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","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\/10095840.pdf?arnumber=10095840","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T13:57:58Z","timestamp":1700488678000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095840\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095840","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}