{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:28:18Z","timestamp":1740101298063,"version":"3.37.3"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100015956","name":"Key Research and Development Program of Guangdong Province","doi-asserted-by":"publisher","award":["2021B 0101400003"],"award-info":[{"award-number":["2021B 0101400003"]}],"id":[{"id":"10.13039\/501100015956","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022892","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"509-516","source":"Crossref","is-referenced-by-count":1,"title":["Learning Invariant Representation and Risk Minimized for Unsupervised Accent Domain Adaptation"],"prefix":"10.1109","author":[{"given":"Chendong","family":"Zhao","sequence":"first","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianzong","family":"Wang","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyang","family":"Qu","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoqian","family":"Wang","sequence":"additional","affiliation":[{"name":"The Shenzhen International Graduate School, Tsinghua University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2020.3045349"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/DSAA54385.2022.10032360"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref5","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Baevski","year":"2020"},{"article-title":"Achieving Multi-Accent ASR via Unsupervised Acoustic Model Adaptation","volume-title":"Interspeech 2020, 21th Annual Conference of the International Speech Communication Association","author":"Ali","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414299"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414833"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413680"},{"key":"ref12","first-page":"10937","article-title":"Unispeech: Unified speech representation learning with labeled and unlabeled data","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","author":"Wang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746051"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2039"},{"article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Baevski","key":"ref15"},{"key":"ref16","article-title":"Unsupervised speech recognition","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Baevski","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1864"},{"article-title":"Achieving multi-accent asr via unsupervised acoustic model adaptation","volume-title":"Interspeech 2020, 21th Annual Conference of the International Speech Communication Association","author":"Ali","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414922"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-349"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3084"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.033"},{"key":"ref23","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Hsu","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref25","first-page":"223","article-title":"The CMU arctic speech databases","volume-title":"Fifth ISCA ITRW on Speech Synthesis","author":"Kominek"},{"article-title":"Categorical reparametrization with gumble-softmax","volume-title":"5th International Conference on Learning Representations, ICLR 2017","author":"Jang","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC-SmartCity-DSS50907.2020.00129"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412109"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.6028\/nist.ir.4930"},{"key":"ref31","first-page":"4211","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)","author":"Ardila","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683535"},{"issue":"11","key":"ref34","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"volume-title":"Indian english \u2014 Wikipedia, the free encyclopedia","year":"2022","key":"ref35"},{"volume-title":"Australian english \u2014 Wikipedia, the free encyclopedia","year":"2022","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref38","article-title":"Signal processing via web services: The use case webmaus","author":"Kisler","year":"2012","journal-title":"Digital Humanities (DH)"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022892.pdf?arnumber=10022892","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:07:58Z","timestamp":1707811678000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022892\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022892","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}