{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T02:32:22Z","timestamp":1743042742260,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030878016"},{"type":"electronic","value":"9783030878023"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-87802-3_28","type":"book-chapter","created":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T23:36:52Z","timestamp":1632267412000},"page":"303-316","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimised Code-Switched Language Model Data Augmentation in Four Under-Resourced South African Languages"],"prefix":"10.1007","author":[{"given":"Joshua","family":"Jansen van Vueren","sequence":"first","affiliation":[]},{"given":"Thomas","family":"Niesler","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,22]]},"reference":[{"key":"28_CR1","unstructured":"Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems. White Paper (2015)"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Biswas, A., van der Westhuizen, E., Niesler, T., de Wet, F.: Improving ASR for code-switched speech in under-resourced languages using out-of-domain data. In: Proceedings of the 6th International Workshop on Spoken Language Technologies for Under-Resourced Languages (SLTU), Gurugram, India (2018)","DOI":"10.21437\/SLTU.2018-26"},{"key":"28_CR3","unstructured":"Biswas, A., Yilmaz, E., de Wet, F., van der Westhuizen, E., Niesler, T.: Semi-supervised development of ASR systems for multilingual code-switched speech in under-resourced languages. In: Proceedings of the 12th Language Resources and Evaluation Conference (LREC), Marseille, France (2020)"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Biswas, A., Y\u0131lmaz, E., de Wet, F., van der Westhuizen, E., Niesler, T.: Semi-supervised acoustic model training for five-lingual code-switched ASR. In: Proceedings of Interspeech, Graz, Austria (2019)","DOI":"10.21437\/Interspeech.2019-1325"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Chang, C.T., Chuang, S.P., Lee, H.Y.: Code-switching sentence generation by generative adversarial networks and its application to data augmentation. In: Proceedings of Interspeech, Graz, Austria (2019)","DOI":"10.21437\/Interspeech.2019-3214"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar (2014)","DOI":"10.3115\/v1\/D14-1179"},{"issue":"11","key":"28_CR7","doi-asserted-by":"publisher","first-page":"1986","DOI":"10.1016\/j.lingua.2004.10.001","volume":"116","author":"M Deuchar","year":"2006","unstructured":"Deuchar, M.: Welsh-English code-switching and the matrix language frame model. Lingua 116(11), 1986\u20132011 (2006)","journal-title":"Lingua"},{"key":"28_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"28_CR9","doi-asserted-by":"crossref","unstructured":"Gao, Y., Feng, J., Liu, Y., Hou, L., Pan, X., Ma, Y.: Code-switching sentence generation by BERT and generative adversarial networks. In: Proceedings of Interspeech, Graz, Austria (2019)","DOI":"10.21437\/Interspeech.2019-2501"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Garg, S., Parekh, T., Jyothi, P.: Code-switched language models using dual RNNs and same-source pretraining. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Brussels, Belgium (2018)","DOI":"10.18653\/v1\/D18-1346"},{"key":"28_CR11","unstructured":"Graves, A.: Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850 (2013)"},{"issue":"8","key":"28_CR12","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Hu, X., Zhang, Q., Yang, L., Gu, B., Xu, X.: Data augmentation for code-switch language modeling by fusing multiple text generation methods. In: Proceedings of Interspeech, Shanghai, China (2020)","DOI":"10.21437\/Interspeech.2020-2219"},{"key":"28_CR14","unstructured":"Jozefowicz, R., Zaremba, W., Sutskever, I.: An empirical exploration of recurrent network architectures. In: Proceedings of the International Conference on Machine Learning (2015)"},{"key":"28_CR15","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Lee, G., Yue, X., Li, H.: Linguistically motivated parallel data augmentation for code-switch language modeling. In: Proceedings of Interspeech, Graz, Austria (2019)","DOI":"10.21437\/Interspeech.2019-1382"},{"key":"28_CR17","volume-title":"Duelling Languages: Grammatical Structure in Codeswitching","author":"C Myers-Scotton","year":"1997","unstructured":"Myers-Scotton, C.: Duelling Languages: Grammatical Structure in Codeswitching. Oxford University Press, Oxford (1997)"},{"key":"28_CR18","unstructured":"Povey, D., et al.: The Kaldi speech recognition toolkit. In: Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Hawaii, USA (2011)"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Stolcke, A.: SRILM-an extensible language modeling toolkit. In: Proceedings of the Seventh International Conference on Spoken Language Processing (ICSLP), Colorado, USA (2002)","DOI":"10.21437\/ICSLP.2002-303"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Taneja, K., Guha, S., Jyothi, P., Abraham, B.: Exploiting monolingual speech corpora for code-mixed speech recognition. In: Proceedings of Interspeech, Graz, Austria (2019)","DOI":"10.21437\/Interspeech.2019-1959"},{"key":"28_CR21","unstructured":"van der Westhuizen, E., Niesler, T.: A first South African corpus of multilingual code-switched soap opera speech. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC). European Language Resources Association (ELRA), Miyazaki (2018)"},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"van der Westhuizen, E., Niesler, T.: Automatic speech recognition of English-isiZulu code-switched speech from South African soap operas. Procedia Comput. Sci. 81, 121\u2013127 (2016). 5th Workshop on Spoken Language Technologies for Under-resourced languages (SLTU), Yogyakarta, Indonesia","DOI":"10.1016\/j.procs.2016.04.039"},{"key":"28_CR23","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.csl.2018.10.002","volume":"54","author":"E van der Westhuizen","year":"2019","unstructured":"van der Westhuizen, E., Niesler, T.R.: Synthesised bigrams using word embeddings for code-switched ASR of four South African language pairs. Comput. Speech Lang. 54, 151\u2013175 (2019)","journal-title":"Comput. Speech Lang."},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Y\u0131lmaz, E., van den Heuvel, H., van Leeuwen, D.: Acoustic and textual data augmentation for improved ASR of code-switching speech. In: Proceedings of Interspeech, Hyderabad, India (2018)","DOI":"10.21437\/Interspeech.2018-52"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87802-3_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T22:00:48Z","timestamp":1673301648000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87802-3_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030878016","9783030878023"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87802-3_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"22 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"St Petersburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2021\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"163","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"74","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"45% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.5","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held online due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}