{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T02:26:56Z","timestamp":1760149616123,"version":"build-2065373602"},"reference-count":64,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Speech & Language"],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1016\/j.csl.2021.101262","type":"journal-article","created":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T11:54:12Z","timestamp":1625140452000},"page":"101262","update-policy":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":15,"special_numbering":"C","title":["Code-switched automatic speech recognition in five South African languages"],"prefix":"10.1016","volume":"71","author":[{"ORCID":"https:\/\/linproxy.fan.workers.dev:443\/https\/orcid.org\/0000-0003-3944-1631","authenticated-orcid":false,"given":"Astik","family":"Biswas","sequence":"first","affiliation":[]},{"given":"Emre","family":"Y\u0131lmaz","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/linproxy.fan.workers.dev:443\/https\/orcid.org\/0000-0002-7430-503X","authenticated-orcid":false,"given":"Ewald","family":"van der Westhuizen","sequence":"additional","affiliation":[]},{"given":"Febe","family":"de Wet","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Niesler","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.csl.2021.101262_b1","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1109\/TASLP.2015.2389622","article-title":"Syntactic and semantic features for code-switching factored language models","volume":"23","author":"Adel","year":"2015","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.csl.2021.101262_b2","series-title":"Proc. ICASSP","article-title":"Recurrent neural network language modeling for code switching conversational speech","author":"Adel","year":"2013"},{"key":"10.1016\/j.csl.2021.101262_b3","series-title":"Proc. IALP","first-page":"137","article-title":"Automatic speech recognition of code switching speech using 1-best rescoring","author":"Ahmed","year":"2012"},{"key":"10.1016\/j.csl.2021.101262_b4","doi-asserted-by":"crossref","unstructured":"Amazouz, D., Adda-Decker, M., Lamel, L., 2017. Addressing code-switching in French\/Algerian Arabic speech. In: Proc. Interspeech. Stockholm, Sweden.","DOI":"10.21437\/Interspeech.2017-1373"},{"key":"10.1016\/j.csl.2021.101262_b5","unstructured":"Amazouz, D., Adda-Decker, M., Lamel, L., 2018. The French-Algerian code-switching triggered audio corpus (FACST). In: Proc. LREC. Miyazaki, Japan."},{"year":"2013","series-title":"Code-Switching in Conversation: Language, Interaction and Identity","author":"Auer","key":"10.1016\/j.csl.2021.101262_b6"},{"key":"10.1016\/j.csl.2021.101262_b7","unstructured":"Barnard, E., Davel, M.H., van Heerden, C., de\u00a0Wet, F., Badenhorst, J., 2014. The NCHLT speech corpus of the South African languages. In: Proc. SLTU. St Petersburg, Russia."},{"issue":"Feb","key":"10.1016\/j.csl.2021.101262_b8","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"Bengio","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.csl.2021.101262_b9","doi-asserted-by":"crossref","unstructured":"Biswas, A., van\u00a0der Westhuizen, E., Niesler, T.R., de\u00a0Wet, F., 2018a. Improving ASR for code-switched speech in under-resourced languages using out-of-domain data. In: Proc. SLTU. Gurugram, India.","DOI":"10.21437\/SLTU.2018-26"},{"key":"10.1016\/j.csl.2021.101262_b10","doi-asserted-by":"crossref","unstructured":"Biswas, A., de\u00a0Wet, F., van\u00a0der Westhuizen, E., Y\u0131lmaz, E., Niesler, T.R., 2018b. Multilingual neural network acoustic modelling for ASR of under-resourced English-isiZulu code-switched speech. In: Proc. Interspeech. Hyderabad, India.","DOI":"10.21437\/Interspeech.2018-1711"},{"key":"10.1016\/j.csl.2021.101262_b11","doi-asserted-by":"crossref","unstructured":"Biswas, A., Y\u0131lmaz, E., de\u00a0Wet, F., van\u00a0der Westhuizen, E., Niesler, T.R., 2019. Semi-supervised acoustic model training for five-lingual code-switched ASR. In: Proc. Interspeech. Graz, Austria.","DOI":"10.21437\/Interspeech.2019-1325"},{"key":"10.1016\/j.csl.2021.101262_b12","series-title":"Varieties of English, Vol. 4","first-page":"164","article-title":"White South African English: phonology","author":"Bowerman","year":"2008"},{"issue":"4","key":"10.1016\/j.csl.2021.101262_b13","first-page":"467","article-title":"Class-based n-gram models of natural language","volume":"18","author":"Brown","year":"1992","journal-title":"Comput. Linguist."},{"key":"10.1016\/j.csl.2021.101262_b14","unstructured":"Cotterell, R., Renduchintala, A., Saphra, N., Callison-Burch, C., 2014. An Algerian Arabic-French code-switched corpus. In: Proc. OSACT. Reykjavik, Iceland."},{"key":"10.1016\/j.csl.2021.101262_b15","unstructured":"Eiselen, R., Puttkammer, M.J., 2014. Developing text resources for ten South African languages. In: Proc. LREC. pp. 3698\u20133703."},{"key":"10.1016\/j.csl.2021.101262_b16","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.specom.2019.04.007","article-title":"IITG-HingCoS corpus: A Hinglish code-switching database for automatic speech recognition","volume":"110","author":"Ganji","year":"2019","journal-title":"Speech Commun."},{"key":"10.1016\/j.csl.2021.101262_b17","series-title":"Proc. ICASSP","article-title":"Multilingual training of deep neural networks","author":"Ghoshal","year":"2013"},{"key":"10.1016\/j.csl.2021.101262_b18","unstructured":"Goldhahn, D., Eckart, T., Quasthoff, U., 2012. Building large monolingual dictionaries at the Leipzig Corpora collection: From 100 to 200 languages. In: Proc. LREC, Vol. 29. Istanbul, Turkey."},{"key":"10.1016\/j.csl.2021.101262_b19","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1016\/j.procs.2017.10.111","article-title":"Building a first language model for code-switch Arabic-English","volume":"117","author":"Hamed","year":"2017","journal-title":"Procedia Comput. Sci."},{"year":"1989","series-title":"Bilinguality & Bilingualism","author":"Hamers","key":"10.1016\/j.csl.2021.101262_b20"},{"year":"2020","series-title":"IARPA Babel project site","key":"10.1016\/j.csl.2021.101262_b21"},{"year":"2020","series-title":"IARPA Babel Zulu language pack IARPA-babel206b-v0.1e","key":"10.1016\/j.csl.2021.101262_b22"},{"issue":"6","key":"10.1016\/j.csl.2021.101262_b23","doi-asserted-by":"crossref","first-page":"1255","DOI":"10.1016\/j.csl.2014.04.005","article-title":"Capitalising on North American speech resources for the development of a South African English large vocabulary speech recognition system","volume":"28","author":"Kamper","year":"2014","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.csl.2021.101262_b24","doi-asserted-by":"crossref","unstructured":"Ko, T., Peddinti, V., Povey, D., Khudanpur, S., 2015. Audio augmentation for speech recognition. In: Proc. Interspeech. Dresden, Germany.","DOI":"10.21437\/Interspeech.2015-711"},{"key":"10.1016\/j.csl.2021.101262_b25","doi-asserted-by":"crossref","first-page":"1174","DOI":"10.1016\/j.sbspro.2013.01.173","article-title":"Intra-sentential and inter-sentential code-switching in Turkish-English bilinguals in New York City, USA","volume":"70","author":"Koban","year":"2013","journal-title":"Procedia-Soc. Behav. Sci."},{"key":"10.1016\/j.csl.2021.101262_b26","unstructured":"Li, Y., Fung, P., 2012. Code-switch language model with inversion constraints for mixed language speech recognition. In: Proc. COLING. Mumbai, India."},{"key":"10.1016\/j.csl.2021.101262_b27","doi-asserted-by":"crossref","unstructured":"Li, Y., Fung, P., 2013. Language modeling for mixed language speech recognition using weighted phrase extraction. In: Proc. Interspeech. Lyon, France.","DOI":"10.21437\/Interspeech.2013-584"},{"key":"10.1016\/j.csl.2021.101262_b28","doi-asserted-by":"crossref","unstructured":"Li, K., Li, J., Ye, G., Zhao, R., Gong, Y., 2019. Towards code-switching ASR for end-to-end CTC models. In: Proc. ICASSP. Brighton, UK.","DOI":"10.1109\/ICASSP.2019.8683223"},{"issue":"3","key":"10.1016\/j.csl.2021.101262_b29","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1007\/s10579-015-9303-x","article-title":"Mandarin\u2013English code-switching speech corpus in South-East Asia: SEAME","volume":"49","author":"Lyu","year":"2015","journal-title":"Lang. Resour. Eval."},{"key":"10.1016\/j.csl.2021.101262_b30","unstructured":"Lyudovyk, T., Pylypenko, V., 2014. Code-switching speech recognition for closely related languages. In: Proc. SLTU. St Petersburg, Russia."},{"year":"2000","series-title":"Bilingual Speech: A Typology of Code-Mixing, Vol. 11","author":"Muysken","key":"10.1016\/j.csl.2021.101262_b31"},{"issue":"3","key":"10.1016\/j.csl.2021.101262_b32","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1111\/j.1467-971X.1989.tb00673.x","article-title":"Code switching with English: types of switching, types of communities","volume":"8","author":"Myers-Scotton","year":"1989","journal-title":"World Engl."},{"key":"10.1016\/j.csl.2021.101262_b33","unstructured":"Pandey, A., Srivastava, B.M.L., Kumar, R., Nellore, B.T., Teja, K.S., Gangashetty, S.V., 2018. Phonetically balanced code-mixed speech corpus for Hindi-English automatic speech recognition. In: Proc. LREC. Miyazaki, Japan."},{"year":"2019","series-title":"Specaugment: A simple data augmentation method for automatic speech recognition","author":"Park","key":"10.1016\/j.csl.2021.101262_b34"},{"issue":"3","key":"10.1016\/j.csl.2021.101262_b35","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1109\/LSP.2017.2723507","article-title":"Low latency acoustic modeling using temporal convolution and LSTMs","volume":"25","author":"Peddinti","year":"2018","journal-title":"IEEE Signal Process. Lett."},{"issue":"7\u20138","key":"10.1016\/j.csl.2021.101262_b36","first-page":"581","article-title":"Sometimes I\u2019ll start a sentence in Spanish y termino en Espanol: toward a typology of code-switching","volume":"18","author":"Poplack","year":"1980","journal-title":"Linguistics"},{"key":"10.1016\/j.csl.2021.101262_b37","doi-asserted-by":"crossref","unstructured":"Povey, D., Cheng, G., Wang, Y., Li, K., Xu, H., Yarmohammadi, M., Khudanpur, S., 2018. Semi-orthogonal low-rank matrix factorization for deep neural networks. In: Proc. Interspeech. Hyderabad, India.","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"10.1016\/j.csl.2021.101262_b38","doi-asserted-by":"crossref","unstructured":"Povey, D., Peddinti, V., Galvez, D., Ghahremani, P., Manohar, V., Na, X., Wang, Y., Khudanpur, S., 2016. Purely sequence-trained neural networks for ASR based on lattice-free MMI. In: Proc. Interspeech. San Francisco, USA.","DOI":"10.21437\/Interspeech.2016-595"},{"key":"10.1016\/j.csl.2021.101262_b39","doi-asserted-by":"crossref","unstructured":"Shan, C., Weng, C., Wang, G., Su, D., Luo, M., Yu, D., Xie, L., 2019. Investigating end-to-end speech recognition for Mandarin-English code-switching. In: Proc. ICASSP. Brighton, UK.","DOI":"10.1109\/ICASSP.2019.8682850"},{"key":"10.1016\/j.csl.2021.101262_b40","doi-asserted-by":"crossref","unstructured":"Singh, A., Tan, T.-P., 2018. Evaluating code-switched Malay-English speech using time delay neural networks. In: Proc. SLTU. Gurugram, India.","DOI":"10.21437\/SLTU.2018-41"},{"key":"10.1016\/j.csl.2021.101262_b41","unstructured":"Sivasankaran, S., Srivastava, B.M.L., Sitaram, S., Bali, K., Choudhury, M., Phone merging for code-switched speech recognition. In: Proc. Third Workshop on Computational Approaches to Linguistic Code-Switching. Melbourne, Australia."},{"year":"2018","series-title":"Hindi-English code-switching speech corpus","author":"Sreeram","key":"10.1016\/j.csl.2021.101262_b42"},{"year":"2012","series-title":"Census in Brief","key":"10.1016\/j.csl.2021.101262_b43"},{"key":"10.1016\/j.csl.2021.101262_b44","doi-asserted-by":"crossref","unstructured":"Stolcke, A., 2002. SRILM - an extensible language modeling toolkit. In: Proc. ICSLP. Denver, USA.","DOI":"10.21437\/ICSLP.2002-303"},{"year":"2017","series-title":"Deep LSTM for large vocabulary continuous speech recognition","author":"Tian","key":"10.1016\/j.csl.2021.101262_b45"},{"key":"10.1016\/j.csl.2021.101262_b46","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.procs.2016.04.039","article-title":"Automatic speech recognition of English-isiZulu code-switched speech from South African soap operas","volume":"81","author":"van der Westhuizen","year":"2016","journal-title":"Procedia Comput. Sci."},{"key":"10.1016\/j.csl.2021.101262_b47","doi-asserted-by":"crossref","unstructured":"van der Westhuizen, E., Niesler, T.R., 2017. Synthesising isiZulu-English code-switch bigrams using word embeddings. In: Proc. Interspeech. Stockholm, Sweden.","DOI":"10.21437\/Interspeech.2017-1437"},{"key":"10.1016\/j.csl.2021.101262_b48","unstructured":"van der Westhuizen, E., Niesler, T.R., 2018. A first South African corpus of multilingual code-switched soap opera speech. In: Proc. LREC. Miyazaki, Japan."},{"key":"10.1016\/j.csl.2021.101262_b49","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.csl.2018.10.002","article-title":"Synthesised bigrams using word embeddings for code-switched ASR of four South African language pairs","volume":"54","author":"van der Westhuizen","year":"2019","journal-title":"Comput. Speech Lang."},{"year":"2007","series-title":"The Grammar of English\/Afrikaans Code Switching","author":"van Dulm","key":"10.1016\/j.csl.2021.101262_b50"},{"key":"10.1016\/j.csl.2021.101262_b51","doi-asserted-by":"crossref","unstructured":"Vu, N.T., Lyu, D.-C., Weiner, J., Telaar, D., Schlippe, T., Blaicher, F., Chng, E.-S., Schultz, T., Li, H., 2012. A first speech recognition system for Mandarin-English code-switch conversational speech. In: Proc. ICASSP. New Orleans, USA.","DOI":"10.1109\/ICASSP.2012.6289015"},{"issue":"3","key":"10.1016\/j.csl.2021.101262_b52","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1109\/29.21701","article-title":"Phoneme recognition using time-delay neural networks","volume":"37","author":"Waibel","year":"1989","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"year":"2002","series-title":"Language in South Africa: The Role of Language in National Transformation, Reconstruction and Development","author":"Webb","key":"10.1016\/j.csl.2021.101262_b53"},{"key":"10.1016\/j.csl.2021.101262_b54","unstructured":"Wilkinson, N., Biswas, A., Y\u0131lmaz, E., De\u00a0Wet, F., van\u00a0der Westhuizen, E., Niesler, T.R., 2020. Semi-supervised acoustic modelling for five-lingual code-switched ASR using automatically-segmented soap opera speech. In: Proc. SLTU. Marseille, France."},{"issue":"3","key":"10.1016\/j.csl.2021.101262_b55","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1017\/S0272263105340204","article-title":"An introduction to contact linguistics","volume":"27","author":"Winkler","year":"2005","journal-title":"Stud. Second Lang. Acquis."},{"key":"10.1016\/j.csl.2021.101262_b56","unstructured":"Y\u0131lmaz, E., Andringa, M., Kingma, S., Van\u00a0der Kuip, F., Van\u00a0de Velde, H., Kampstra, F., Algra, J., Van\u00a0den Heuvel, H., Van\u00a0Leeuwen, D.A., 2016a. A longitudinal bilingual Frisian-Dutch radio broadcast database designed for code-switching research. In: Proc. LREC. Portoro\u017e, Slovenia."},{"key":"10.1016\/j.csl.2021.101262_b57","doi-asserted-by":"crossref","unstructured":"Y\u0131lmaz, E., Biswas, A., van\u00a0der Westhuizen, E., de\u00a0Wet, F., Niesler, T.R., 2018a. Building a unified code-switching ASR system for South African languages. In: Proc. Interspeech. Hyderabad, India.","DOI":"10.21437\/Interspeech.2018-1966"},{"key":"10.1016\/j.csl.2021.101262_b58","series-title":"Proc. SLT","article-title":"Code-switching detection using multilingual DNNs","author":"Y\u0131lmaz","year":"2016"},{"key":"10.1016\/j.csl.2021.101262_b59","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.procs.2016.04.044","article-title":"Investigating bilingual deep neural networks for automatic recognition of code-switching Frisian speech","volume":"81","author":"Y\u0131lmaz","year":"2016","journal-title":"Procedia Comput. Sci."},{"key":"10.1016\/j.csl.2021.101262_b60","doi-asserted-by":"crossref","unstructured":"Y\u0131lmaz, E., van\u00a0den Heuvel, H., van Leeuwen, D.A., 2018b. Acoustic and textual data augmentation for improved ASR of code-switching speech. In: Proc. Interspeech. Hyderabad, India.","DOI":"10.21437\/Interspeech.2018-52"},{"key":"10.1016\/j.csl.2021.101262_b61","series-title":"Proc. ASRU","article-title":"Language diarization for semi-supervised bilingual acoustic model training","author":"Y\u0131lmaz","year":"2017"},{"key":"10.1016\/j.csl.2021.101262_b62","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.specom.2018.10.006","article-title":"Semi-supervised acoustic model training for speech with code-switching","volume":"105","author":"Y\u0131lmaz","year":"2018","journal-title":"Speech Commun."},{"year":"2014","series-title":"Recurrent neural network regularization","author":"Zaremba","key":"10.1016\/j.csl.2021.101262_b63"},{"year":"2018","series-title":"On the end-to-end solution to Mandarin-English code-switching speech recognition","author":"Zeng","key":"10.1016\/j.csl.2021.101262_b64"}],"container-title":["Computer Speech & Language"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S088523082100067X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S088523082100067X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:43:45Z","timestamp":1760129025000},"score":1,"resource":{"primary":{"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/linkinghub.elsevier.com\/retrieve\/pii\/S088523082100067X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1]]},"references-count":64,"alternative-id":["S088523082100067X"],"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.1016\/j.csl.2021.101262","relation":{},"ISSN":["0885-2308"],"issn-type":[{"type":"print","value":"0885-2308"}],"subject":[],"published":{"date-parts":[[2022,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Code-switched automatic speech recognition in five South African languages","name":"articletitle","label":"Article Title"},{"value":"Computer Speech & Language","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.1016\/j.csl.2021.101262","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2021 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"101262"}}