{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:01:33Z","timestamp":1764403293818,"version":"build-2065373602"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"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":[[2023,10,31]]},"DOI":"10.1109\/apsipaasc58517.2023.10317410","type":"proceedings-article","created":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:07:46Z","timestamp":1700507266000},"page":"344-349","source":"Crossref","is-referenced-by-count":6,"title":["Learning Adapters for Code-Switching Speech Recognition"],"prefix":"10.1109","author":[{"given":"Chun-Yi","family":"He","sequence":"first","affiliation":[{"name":"National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Hsinchu,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jen-Tzung","family":"Chien","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Hsinchu,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289015"},{"key":"ref2","first-page":"1671","article-title":"Code switching language model with translation constraint for mixed language speech recognition","volume-title":"Proc. of International Conference on Computational Linguistics","author":"Li"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2191955"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2173371"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2197156"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107295360"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref8","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume-title":"Proc. of International Conference on Machine Learning","author":"Graves"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref10","article-title":"Attention-based models for speech recognition","volume":"28","author":"Chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3166400"},{"article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","year":"2020","author":"Zhang","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-872"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688231"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639084"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639081"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682674"},{"article-title":"Share or not? learning to schedule language-specific capacity for multilingual translation","volume-title":"Proc. of International Conference on Learning Representations","author":"Zhang","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1429"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2143405"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462180"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.1996.481450"},{"article-title":"Modeling code-switching speech on under-resourced languages for language identification","volume-title":"Proc. of Workshop on Spoken Language Technologies for Under-resourced Languages","author":"Mabokela","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1578"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1035"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.348"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2488"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462557"},{"key":"ref30","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"ASCEND: A spontaneous chinese-english dataset for code-switching in multi-turn conversation","volume-title":"Proc. of International Conference on Language Resources and Evaluation","author":"Lovenia","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682386"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-44"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2499302"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3068187"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2858"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1165"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-545"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10457"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9979949"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2021-329","article-title":"Unsupervised cross-lingual representation learning for speech recognition","volume-title":"Proc. of Annual Conference of International Speech Communication Association","author":"Conneau"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref45","first-page":"4211","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. of Conference on Language Resources and Evaluation","author":"Ardila"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.818114"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1017\/9781108552332"}],"event":{"name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2023,10,31]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,11,3]]}},"container-title":["2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10317071\/10317095\/10317410.pdf?arnumber=10317410","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T18:56:53Z","timestamp":1709405813000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10317410\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,31]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc58517.2023.10317410","relation":{},"subject":[],"published":{"date-parts":[[2023,10,31]]}}}