{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:17:41Z","timestamp":1753600661421},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389760","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-7","source":"Crossref","is-referenced-by-count":3,"title":["Building High-Accuracy Multilingual ASR With Gated Language Experts and Curriculum Training"],"prefix":"10.1109","author":[{"given":"Eric","family":"Sun","sequence":"first","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Hu","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yimeng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Zhou","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Xue","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peidong","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linquan","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shujie","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edward","family":"Lin","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Gong","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"article-title":"Sequence Transduction with Recurrent Neural Networks","volume-title":"Proc. of the 29th ICML","author":"Graves","key":"ref4"},{"article-title":"Streaming Endto-End Speech Recognition for Mobile Devices","volume-title":"Proc. ICASSP","author":"He","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003906"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref8","article-title":"TransformerTransducer: End-to-End Speech Recognition with Self-Attention","author":"Yeh","year":"2019","journal-title":"arxiv.org\/abs\/1910.12977"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413535"},{"year":"2021","key":"ref10","article-title":"Multilingual People"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268945"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461972"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682674"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2831"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1009"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2858"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2847"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003870"},{"key":"ref19","article-title":"Streaming End-to-End Bilingual ASR Systems with Joint Language Identification","author":"Punjabi","year":"2020","journal-title":"arXiv preprint arXiv:2007.03900"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747905"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11249"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1949"},{"journal-title":"arxiv.org\/abs\/2212.04356","article-title":"Robust Speech Recognition via Large-Scale Weak Supervision","author":"Radford","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022937"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096228"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094903"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1055"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1667"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-480"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2485"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413562"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414379"},{"key":"ref33","first-page":"5998","article-title":"Attention is All You Need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2023,12,16]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389760.pdf?arnumber=10389760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:30:00Z","timestamp":1706027400000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389760\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389760","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}