{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T00:27:04Z","timestamp":1768436824040,"version":"3.49.0"},"reference-count":22,"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\/icassp43922.2022.9746282","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8017-8021","source":"Crossref","is-referenced-by-count":11,"title":["Multilingual Text-To-Speech Training Using Cross Language Voice Conversion And Self-Supervised Learning Of Speech Representations"],"prefix":"10.1109","author":[{"given":"Jilong","family":"Wu","sequence":"first","affiliation":[{"name":"Facebook AI"}]},{"given":"Adam","family":"Polyak","sequence":"additional","affiliation":[{"name":"Facebook AI"}]},{"given":"Yaniv","family":"Taigman","sequence":"additional","affiliation":[{"name":"Facebook AI"}]},{"given":"Jason","family":"Fong","sequence":"additional","affiliation":[{"name":"The University of Edinburgh"}]},{"given":"Prabhav","family":"Agrawal","sequence":"additional","affiliation":[{"name":"Facebook AI"}]},{"given":"Qing","family":"He","sequence":"additional","affiliation":[{"name":"Facebook AI"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-017-0659-6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-179"},{"key":"ref12","article-title":"Building multi lingual tts using cross lingual voice conversion","author":"sun","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1163"},{"key":"ref14","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1416"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1862"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414853"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.1005751"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2668"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IALP.2017.8300579"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414809"},{"key":"ref7","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020"},{"key":"ref2","first-page":"2410","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref1","article-title":"Unsupervised cross-lingual representation learning for speech recognition","author":"conneau","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852225"},{"key":"ref20","article-title":"Autoencoding beyond pixels using a learned similarity metric","author":"boesen","year":"2016","journal-title":"ICML"},{"key":"ref22","year":"2015","journal-title":"The International Phonetic Alphabet"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"}],"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\/09746282.pdf?arnumber=9746282","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:09:46Z","timestamp":1661198986000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746282\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746282","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}