{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T14:04:26Z","timestamp":1779890666313,"version":"3.53.1"},"reference-count":30,"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\/asru57964.2023.10389798","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":10,"title":["BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognition"],"prefix":"10.1109","author":[{"given":"Peikun","family":"Chen","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Yu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhao","family":"Liang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongfei","family":"Xue","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xucheng","family":"Wan","sequence":"additional","affiliation":[{"name":"Huawei Technologies,IT Innovation and Research Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naijun","family":"Zheng","sequence":"additional","affiliation":[{"name":"Huawei Technologies,IT Innovation and Research Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Huawei Technologies,IT Innovation and Research Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3328283"},{"key":"ref2","first-page":"577","article-title":"Attention-based models for speech recognition","volume-title":"Proc.NIPS","author":"Chorowski"},{"key":"ref3","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc.NIPS","author":"Vaswani"},{"key":"ref4","article-title":"Sequence transduction with recurrent neural networks","volume":"abs\/1211.3711","author":"Graves","year":"2012","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1353\/lan.2002.0114"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1974"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683223"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097151"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413562"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11426"},{"key":"ref11","article-title":"The ASRU 2019 mandarin-english code-switching speech recognition challenge: Open datasets, tracks, methods and results","volume":"abs\/2007.05916","author":"Shi","year":"2020","journal-title":"CoRR"},{"key":"ref12","first-page":"24","article-title":"First workshop on speech processing for code-switching in multilingual communities: Shared task on code-switched spoken language identification","volume-title":"Proc.WSTCSMC","author":"Shah"},{"key":"ref13","article-title":"A survey of codeswitched speech and language processing","volume":"abs\/1904.00784","author":"Sitaram","year":"2019","journal-title":"CoRR"},{"key":"ref14","article-title":"Reducing language context confusion for end-to-end code-switching automatic speech recognition","volume-title":"CoRR","volume":"abs\/2201.12155","author":"Zhang"},{"key":"ref15","article-title":"Language-specific acoustic boundary learning for mandarin-english code-switching speech recognition","volume":"abs\/2306.05279","author":"Fan","year":"2023","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1365"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2488"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2485"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-923"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747537"},{"key":"ref21","article-title":"Internal language model estimation based language model fusion for cross-domain code-switching speech recognition","volume":"abs\/2207.04176","author":"Peng","year":"2022","journal-title":"CoRR"},{"key":"ref22","article-title":"Monolingual recognizers fusion for code-switching speech recognition","volume":"abs\/2211.01046","author":"Song","year":"2022","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054250"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688238"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3138674"},{"key":"ref26","article-title":"A structured self-attentive sentence embedding","volume-title":"Proc. ICLR. 2017","author":"Lin"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"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\/10389798.pdf?arnumber=10389798","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:30:52Z","timestamp":1706027452000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389798\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389798","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}