{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:36:22Z","timestamp":1767339382817,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096929","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["CROSSSPEECH: Speaker-Independent Acoustic Representation for Cross-Lingual Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Ji-Hoon","family":"Kim","sequence":"first","affiliation":[{"name":"42dot Inc.,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong-Sun","family":"Yang","sequence":"additional","affiliation":[{"name":"42dot Inc.,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoon-Cheol","family":"Ju","sequence":"additional","affiliation":[{"name":"42dot Inc.,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Il-Hwan","family":"Kim","sequence":"additional","affiliation":[{"name":"42dot Inc.,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byeong-Yeol","family":"Kim","sequence":"additional","affiliation":[{"name":"42dot Inc.,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"ref3","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-toend text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3356232\/mm1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-925"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2070"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-474"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682674"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1821"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.472"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2668"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414226"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-46"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747707"},{"key":"ref15","first-page":"3915","article-title":"Feature-critic networks for heterogeneous domain generalization","volume-title":"International Conference on Machine Learning","author":"Li"},{"journal-title":"Generspeech: Towards style transfer for generalizable out-of-domain text-to-speech synthesis","year":"2022","author":"Huang","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747388"},{"article-title":"Domain generalization with mixstyle","volume-title":"Proc. International Conference on Learning Representation","author":"Zhou","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00699"},{"volume-title":"The LJ Speech Dataset","year":"2017","author":"Ito","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03958"},{"article-title":"Large batch optimization for deep learning: training BERT in 76 minutes","volume-title":"Proc. International Conference on Learning Representation","author":"You","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-845"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-126"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"issue":"11","key":"ref27","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096929.pdf?arnumber=10096929","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T22:54:26Z","timestamp":1709247266000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096929\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096929","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}