{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T02:30:29Z","timestamp":1768444229884,"version":"3.49.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747801","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"7912-7916","source":"Crossref","is-referenced-by-count":4,"title":["Using Multiple Reference Audios and Style Embedding Constraints for Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Cheng","family":"Gong","sequence":"first","affiliation":[{"name":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenhua","family":"Ling","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ju","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huiyan Technology (Tianjin) Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwu","family":"Dang","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"A generative adversarial network for style modeling in a text-to-speech system","volume":"2","author":"ma","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413696"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1411"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639672"},{"key":"ref15","article-title":"Neural tts stylization with adversarial and collaborative games","author":"ma","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054591"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414226"},{"key":"ref18","article-title":"Maximizing mutual information for tacotron","author":"liu","year":"2019","journal-title":"arXiv preprint arXiv 1909 01771"},{"key":"ref19","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT (1)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-852"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref6","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry-ryan","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref5","article-title":"A survey on neural speech synthesis","author":"tan","year":"2021","journal-title":"arXiv preprint arXiv 2106 13112"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1113"},{"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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref1","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proceedings of the Annual Conference of the International Speech Communication Association INTER-SPEECH"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref20","author":"xiao","year":"2018","journal-title":"bert-as-service"},{"key":"ref22","first-page":"2410","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning"},{"key":"ref21","first-page":"531","article-title":"Mutual information neural estimation","author":"belghazi","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref23","year":"2019","journal-title":"Jiwer Similarity measures for automatic speech recognition evaluation"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747801.pdf?arnumber=9747801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:07:49Z","timestamp":1660594069000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747801\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747801","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}