{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T15:31:08Z","timestamp":1771515068144,"version":"3.50.1"},"reference-count":19,"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\/icassp43922.2022.9746914","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"6072-6076","source":"Crossref","is-referenced-by-count":5,"title":["Improving Cross-Lingual Speech Synthesis with Triplet Training Scheme"],"prefix":"10.1109","author":[{"given":"Jianhao","family":"Ye","sequence":"first","affiliation":[{"name":"Ximalaya Inc.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongbin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Ximalaya Inc.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiba","family":"Su","sequence":"additional","affiliation":[{"name":"Ximalaya Inc.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wendi","family":"He","sequence":"additional","affiliation":[{"name":"Ximalaya Inc.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaimeng","family":"Ren","sequence":"additional","affiliation":[{"name":"Ximalaya Inc.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Li","sequence":"additional","affiliation":[{"name":"Ximalaya Inc.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heng","family":"Lu","sequence":"additional","affiliation":[{"name":"Ximalaya Inc.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Using ipa-based tacotron for data efficient cross-lingual speaker adaptation and pronunciation enhancement","author":"hemati","year":"2020"},{"key":"ref11","first-page":"1599","article-title":"Improve cross-lingual text-to-speech synthesis on monolingual corpora with pitch contour information","author":"zhan","year":"2021","journal-title":"InterSpeech"},{"key":"ref12","first-page":"4442","article-title":"Multi-reference neural TTS stylization with adversarial cycle consistency","author":"whitehill","year":"2020","journal-title":"InterSpeech"},{"key":"ref13","first-page":"1614","article-title":"Cross-lingual speaker adaptation using domain adaptation and speaker consistency loss for text-to-speech synthesis","author":"xin","year":"2021","journal-title":"InterSpeech"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1244"},{"key":"ref16","article-title":"Chinese standard mandarin speech corpus","author":"china","year":"2017"},{"key":"ref17","article-title":"The lj speech dataset","author":"ito","year":"2017"},{"key":"ref18","first-page":"4","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"0"},{"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":"ref4","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2968"},{"key":"ref6","article-title":"Multilingual byte2speech text-to-speech models are few-shot spoken language learners","author":"he","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2668"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1163"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682674"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414226"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053094"}],"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\/09746914.pdf?arnumber=9746914","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T16:11:56Z","timestamp":1661184716000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746914\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746914","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}