{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:38:22Z","timestamp":1730230702171,"version":"3.28.0"},"reference-count":26,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747481","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"8027-8031","source":"Crossref","is-referenced-by-count":3,"title":["Zero-Shot Cross-Lingual Transfer Using Multi-Stream Encoder and Efficient Speaker Representation"],"prefix":"10.1109","author":[{"given":"Yibin","family":"Zheng","sequence":"first","affiliation":[{"name":"Tencent Inc,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zewang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent Inc,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinhui","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent Inc,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenchao","family":"Su","sequence":"additional","affiliation":[{"name":"Tencent Inc,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Lu","sequence":"additional","affiliation":[{"name":"Tencent Inc,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"2648","article-title":"Multi-language multi-speaker acoustic modeling for LSTM-RNN based statistical parametric speech synthesis","author":"li","year":"2017","journal-title":"InterSpeech"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682674"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683519"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3191"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2668"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682927"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1249"},{"key":"ref17","article-title":"Multi-stream transformers","author":"burtsev","year":"2021","journal-title":"arXiv preprint arXiv 2107 10342"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1590"},{"key":"ref19","first-page":"2962","article-title":"Deep Voice 2: Multi-speaker neural text-to-speech","author":"gibiansky","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Uncovering latent style factors for expressive speech synthesis","author":"wang","year":"2017","journal-title":"arXiv preprint arXiv 1711 00540"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2935807"},{"key":"ref6","first-page":"5167","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume":"80","author":"wang","year":"2018","journal-title":"Proceedings of the ICML International Conference on Machine Learning"},{"key":"ref5","first-page":"4700","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with Tacotron","volume":"80","author":"skerry-ryan","year":"2018","journal-title":"Proceedings of the ICML International Conference on Machine Learning"},{"article-title":"Sample efficient adaptive text-to-speech","year":"0","author":"chen","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1705"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2187195"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"InterSpeech"},{"key":"ref20","article-title":"VoiceLoop: Voice fitting and synthesis via a phonological loop","author":"taigman","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref22","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"ganin","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413396"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1156"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"3rd International Conference on Learning Representations ICLR 2015 Conference Track Proceedings"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","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\/09747481.pdf?arnumber=9747481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T16:12:54Z","timestamp":1661184774000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747481\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747481","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}