{"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":1775326248823,"version":"3.50.1"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747537","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6412-6416","source":"Crossref","is-referenced-by-count":12,"title":["Joint Modeling of Code-Switched and Monolingual ASR via Conditional Factorization"],"prefix":"10.1109","author":[{"given":"Brian","family":"Yan","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,USA"}]},{"given":"Chunlei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,USA"}]},{"given":"Meng","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,USA"}]},{"given":"Shi-Xiong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,USA"}]},{"given":"Siddharth","family":"Dalmia","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}]},{"given":"Dan","family":"Berrebbi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}]},{"given":"Chao","family":"Weng","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,China"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,USA"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683223"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3209"},{"key":"ref33","article-title":"Learning to recognize code-switched speech without forgetting monolingual speech recognition","author":"shah","year":"2020"},{"key":"ref32","article-title":"Linguistically motivated parallel data augment for code-switch language modeling","author":"lee","year":"2019","journal-title":"InterSpeech"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682824"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1143"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639083"},{"key":"ref36","article-title":"Integration of language identification into a recognition system for spoken conversations containing code-switches","author":"weiner","year":"2012","journal-title":"Proc SLTU"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CHINSL.2004.1409644"},{"key":"ref34","article-title":"A survey of code-switched speech and language processing","author":"sitaram","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053775"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682490"},{"key":"ref29","article-title":"Code-switching sentence generation by generative adversarial networks and its application to data augmentation","author":"chang","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/9781118540190.wbeic006"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.4324\/9780203017883"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682850"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2485"},{"key":"ref21","article-title":"Rnn-t with language bias for end-to-end man-eng code-switching speech recognition","author":"zhang","year":"2021","journal-title":"ISCSLP"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413562"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2488"},{"key":"ref26","article-title":"Language modeling for code-switching: Evaluation, integration of monolingual data, and discriminative training","author":"gonen","year":"2018","journal-title":"Proc EMNLP"},{"key":"ref25","article-title":"Decoupling pronunciation and language for end-to-end code-switching asr","author":"zhang","year":"2021","journal-title":"Proc ICASSP"},{"key":"ref50","article-title":"Neural machine translation of rare words with subword units","author":"sennrich","year":"2015","journal-title":"Proc ACL"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1944"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682674"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref11","article-title":"A configurable multilingual model is all you need to recognize all languages","author":"zhou","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462180"},{"key":"ref13","article-title":"Code-switching speech recognition for closely related languages","author":"lyudovyk","year":"2014","journal-title":"Proc SLTU"},{"key":"ref14","article-title":"Towards end-to-end code-switching speech recognition","author":"luo","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3202"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2016.04.044"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IALP.2017.8300538"},{"key":"ref18","article-title":"On end-to-end mandarin-english code-switching speech recognition","author":"zeng","year":"2018","journal-title":"InterSpeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462201"},{"key":"ref4","article-title":"A study of types and characteristics of code-switching in mandarin-english speech","author":"hou","year":"2020","journal-title":"Proc WSTCSMC"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/1467-8721.00140"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2911"},{"key":"ref5","article-title":"What code-switching strategies are effective in dialog systems?","author":"ahn","year":"2020","journal-title":"Proc SCiL"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1009"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/2158244019853920"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2831"},{"key":"ref46","year":"2017","journal-title":"King-asr-190 Chinese english speech recognition corpus"},{"key":"ref45","article-title":"The asru 2019 mandarin-english code-switching speech recognition challenge: Open datasets, tracks, methods and results","author":"shi","year":"2020","journal-title":"Proc WSTCSMC"},{"key":"ref48","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref42","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2015"},{"key":"ref41","article-title":"Sequence Transduction with Recurrent Neural Networks","author":"graves","year":"2012","journal-title":"Proc ICML"},{"key":"ref44","article-title":"Enforcing encoder-decoder modularity in sequence-to-sequence models","author":"dalmia","year":"2019"},{"key":"ref43","article-title":"Global training of doc processing systems using graph transformer networks","author":"bottou","year":"1997","journal-title":"CVPR"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747537.pdf?arnumber=9747537","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:07:19Z","timestamp":1660594039000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747537\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747537","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}