{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:24:12Z","timestamp":1759332252952,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414226","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6608-6612","source":"Crossref","is-referenced-by-count":18,"title":["Disentangled Speaker and Language Representations Using Mutual Information Minimization and Domain Adaptation for Cross-Lingual TTS"],"prefix":"10.1109","author":[{"given":"Detai","family":"Xin","sequence":"first","affiliation":[{"name":"LINE Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"Komatsu","sequence":"additional","affiliation":[{"name":"LINE Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinnosuke","family":"Takamichi","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Saruwatari","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology, The University of Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682259"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054305"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683519"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2070"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053094"},{"key":"ref15","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":"ref16","article-title":"Learning disentangled representations via mutual information estimation","author":"sanchez","year":"2019","journal-title":"arXiv preprint arXiv 1912 03915"},{"key":"ref17","article-title":"Domain agnostic learning with disentangled representations","author":"peng","year":"2019","journal-title":"arXiv preprint arXiv 1904 12848"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_45"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref4","first-page":"3683","article-title":"Fitting new speakers based on a short untranscribed sample","author":"nachmani","year":"2018","journal-title":"Proc ICML"},{"key":"ref27","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683561"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IALP.2017.8300579"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-172"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2668"},{"key":"ref7","first-page":"4052","article-title":"Deep neural networks for small footprint text-dependent speaker verification","author":"variani","year":"2014","journal-title":"Proc ICASSP"},{"key":"ref2","first-page":"10019","article-title":"Neural voice cloning with a few samples","author":"arik","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1632"},{"key":"ref1","first-page":"4480","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref20","article-title":"Club: A contrastive log-ratio upper bound of mutual information","author":"cheng","year":"2020","journal-title":"arXiv preprint arXiv 2006 12661"},{"key":"ref22","article-title":"JVS corpus: free Japanese multi-speaker voice corpus","author":"takamichi","year":"2019","journal-title":"arXiv preprint arXiv 1908 00310"},{"journal-title":"CSTR VCTK corpus English multi-speaker corpus for cstr voice cloning toolkit","year":"2016","author":"veaux","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref23","article-title":"Word-based partial annotation for efficient corpus construction","author":"neubig","year":"2010","journal-title":"Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC’10)"},{"key":"ref26","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv preprint arXiv 1607 06450"},{"key":"ref25","article-title":"Deep speaker: an end-to-end neural speaker embedding system","author":"li","year":"2017","journal-title":"arXiv preprint arXiv 1705 02304"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414226.pdf?arnumber=9414226","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:20:30Z","timestamp":1659486030000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414226\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414226","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}