{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T18:10:48Z","timestamp":1775326248126,"version":"3.50.1"},"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\/icassp49357.2023.10095878","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":21,"title":["Reducing Language Confusion for Code-Switching Speech Recognition with Token-Level Language Diarization"],"prefix":"10.1109","author":[{"given":"Hexin","family":"Liu","sequence":"first","affiliation":[{"name":"Bytedance"}]},{"given":"Haihua","family":"Xu","sequence":"additional","affiliation":[{"name":"Bytedance"}]},{"given":"Leibny Paola","family":"Garcia","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,CLSP and HLT-COE,USA"}]},{"given":"Andy W. H.","family":"Khong","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,School of Electrical and Electronic Engineering,Singapore"}]},{"given":"Yi","family":"He","sequence":"additional","affiliation":[{"name":"Bytedance"}]},{"given":"Sanjeev","family":"Khudanpur","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,CLSP and HLT-COE,USA"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639083"},{"key":"ref12","first-page":"297","article-title":"An investigation of codeswitching attitude dependent language modeling","author":"vu","year":"2013","journal-title":"Proc SLSP"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461972"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-82"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-354"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-69"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref1","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE Workshop Autom Speech Recognit Understanding"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2858"},{"key":"ref19","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2389622"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1938"},{"key":"ref20","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","author":"ganin","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-563"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3201445"},{"key":"ref8","first-page":"5884","article-title":"Speech-transformer: A norecurrence sequence-to-sequence model for speech recognition","author":"dong","year":"2018","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413562"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10286"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2485"},{"key":"ref3","first-page":"2165","article-title":"On the end-to-end solution to mandarin-english codeswitching speech recognition","author":"zeng","year":"2019","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11426"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054138"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"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\/10095878.pdf?arnumber=10095878","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:00:50Z","timestamp":1700506850000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095878\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095878","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}