{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:40:11Z","timestamp":1755888011340,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T00:00:00Z","timestamp":1720396800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,8]]},"DOI":"10.1145\/3640794.3665579","type":"proceedings-article","created":{"date-parts":[[2024,7,7]],"date-time":"2024-07-07T06:24:56Z","timestamp":1720333496000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["\"\u00bfTe vienes? Sure!\" Joint Fine-tuning of Language Detection and Transcription Improves Automatic Recognition of Code-Switching Speech"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5229-468X","authenticated-orcid":false,"given":"Leopold","family":"Hillah","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Luxembourg, Luxembourg"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8250-3370","authenticated-orcid":false,"given":"Mateusz","family":"Dubiel","sequence":"additional","affiliation":[{"name":"University of Luxembourg, Luxembourg"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5011-1847","authenticated-orcid":false,"given":"Luis A.","family":"Leiva","sequence":"additional","affiliation":[{"name":"University of Luxembourg, Luxembourg"}]}],"member":"320","published-online":{"date-parts":[[2024,7,8]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n. d.]. OpenSLR Open Speech and Language Resources. https:\/\/www.openslr.org\/. Accessed: 2024-02-11."},{"key":"e_1_3_2_1_2_1","volume-title":"What code-switching strategies are effective in dialogue systems?Society for Computation in Linguistics 3, 1","author":"Ahn Emily","year":"2020","unstructured":"Emily Ahn, Cecilia Jimenez, Yulia Tsvetkov, and Alan Black. 2020. What code-switching strategies are effective in dialogue systems?Society for Computation in Linguistics 3, 1 (2020)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Larissa Aronin and David Singleton. 2012. Multilingualism. Vol.\u00a030. John Benjamins Publishing.","DOI":"10.1075\/impact.30"},{"key":"e_1_3_2_1_4_1","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in Neural Information Processing Systems 33 (2020), 12449\u201312460.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3902"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5539\/elt.v11n6p93"},{"key":"e_1_3_2_1_7_1","first-page":"397","article-title":"Receptive vocabulary differences in monolingual and bilingual adults. Bilingualism","volume":"15","author":"Bialystok Ellen","year":"2012","unstructured":"Ellen Bialystok and Gigi Luk. 2012. Receptive vocabulary differences in monolingual and bilingual adults. Bilingualism: Language and Cognition 15, 2 (2012), 397\u2013401.","journal-title":"Language and Cognition"},{"key":"e_1_3_2_1_8_1","unstructured":"Dan Biderman Jose\u00a0Gonzalez Ortiz Jacob Portes Mansheej Paul Philip Greengard Connor Jennings Daniel King Sam Havens Vitaliy Chiley Jonathan Frankle Cody Blakeney and John\u00a0P. Cunningham. 2024. LoRA Learns Less and Forgets Less. arxiv:2405.09673\u00a0[cs.LG]"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3208"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581445"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543829.3544511"},{"key":"e_1_3_2_1_12_1","volume-title":"FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech. arxiv:2205.12446\u00a0[cs.CL]","author":"Conneau Alexis","year":"2022","unstructured":"Alexis Conneau, Min Ma, Simran Khanuja, Yu Zhang, Vera Axelrod, Siddharth Dalmia, Jason Riesa, Clara Rivera, and Ankur Bapna. 2022. FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech. arxiv:2205.12446\u00a0[cs.CL]"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.21832\/9781783091713-008"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.calcs-1.7"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1339"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.131"},{"key":"e_1_3_2_1_17_1","volume-title":"The People\u2019s Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage. CoRR abs\/2111.09344","author":"Galvez Daniel","year":"2021","unstructured":"Daniel Galvez, Greg Diamos, Juan Ciro, Juan\u00a0Felipe Cer\u00f3n, Keith Achorn, Anjali Gopi, David Kanter, Maximilian Lam, Mark Mazumder, and Vijay\u00a0Janapa Reddi. 2021. The People\u2019s Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage. CoRR abs\/2111.09344 (2021). arXiv:2111.09344https:\/\/arxiv.org\/abs\/2111.09344"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Penelope Gardner-Chloros. 2009. Code-Switching. Cambridge university press.","DOI":"10.1017\/CBO9780511609787"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-industry.26"},{"volume-title":"Life as a bilingual: Knowing and using two or more languages","author":"Grosjean Fran\u00e7ois","key":"e_1_3_2_1_20_1","unstructured":"Fran\u00e7ois Grosjean. 2021. Life as a bilingual: Knowing and using two or more languages. Cambridge University Press."},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of The 12th Language Resources and Evaluation Conference (LREC). European Language Resources Association (ELRA)","author":"Guevara-Rukoz Adriana","year":"2020","unstructured":"Adriana Guevara-Rukoz, Isin Demirsahin, Fei He, Shan-Hui\u00a0Cathy Chu, Supheakmungkol Sarin, Knot Pipatsrisawat, Alexander Gutkin, Alena Butryna, and Oddur Kjartansson. 2020. Crowdsourcing Latin American Spanish for Low-Resource Text-to-Speech. In Proceedings of The 12th Language Resources and Evaluation Conference (LREC). European Language Resources Association (ELRA), Marseille, France, 6504\u20136513. https:\/\/www.aclweb.org\/anthology\/2020.lrec-1.801"},{"volume-title":"Discourse strategies. Number\u00a01","author":"Gumperz J","key":"e_1_3_2_1_22_1","unstructured":"John\u00a0J Gumperz. 1982. Discourse strategies. Number\u00a01. Cambridge University Press."},{"key":"e_1_3_2_1_23_1","volume-title":"Towards a unified view of parameter-efficient transfer learning. arXiv preprint arXiv:2110.04366","author":"He Junxian","year":"2021","unstructured":"Junxian He, Chunting Zhou, Xuezhe Ma, Taylor Berg-Kirkpatrick, and Graham Neubig. 2021. Towards a unified view of parameter-efficient transfer learning. arXiv preprint arXiv:2110.04366 (2021)."},{"volume-title":"TEDx Spanish Corpus. Audio and transcripts in Spanish taken from the TEDx Talks","author":"Hernandez-Mena D.","key":"e_1_3_2_1_24_1","unstructured":"Carlos\u00a0D. Hernandez-Mena. 2019. TEDx Spanish Corpus. Audio and transcripts in Spanish taken from the TEDx Talks; shared under the CC BY-NC-ND 4.0 license. Web Download."},{"key":"e_1_3_2_1_25_1","volume-title":"International Conference on Machine Learning. PMLR, 2790\u20132799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De\u00a0Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International Conference on Machine Learning. PMLR, 2790\u20132799."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389644"},{"key":"e_1_3_2_1_27_1","volume-title":"Does bilingualism hamper lexical access in speech production?Acta psychologica 127, 2","author":"Ivanova Iva","year":"2008","unstructured":"Iva Ivanova and Albert Costa. 2008. Does bilingualism hamper lexical access in speech production?Acta psychologica 127, 2 (2008), 277\u2013288."},{"key":"e_1_3_2_1_28_1","volume-title":"Adaptive mixtures of local experts. Neural computation 3, 1","author":"Jacobs A","year":"1991","unstructured":"Robert\u00a0A Jacobs, Michael\u00a0I Jordan, Steven\u00a0J Nowlan, and Geoffrey\u00a0E Hinton. 1991. Adaptive mixtures of local experts. Neural computation 3, 1 (1991), 79\u201387."},{"key":"e_1_3_2_1_29_1","volume-title":"Hierarchical mixtures of experts and the EM algorithm. Neural computation 6, 2","author":"Jordan I","year":"1994","unstructured":"Michael\u00a0I Jordan and Robert\u00a0A Jacobs. 1994. Hierarchical mixtures of experts and the EM algorithm. Neural computation 6, 2 (1994), 181\u2013214."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543829.3544526"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413376"},{"key":"e_1_3_2_1_32_1","volume-title":"Kingma and Jimmy Ba","author":"P.","year":"2017","unstructured":"Diederik\u00a0P. Kingma and Jimmy Ba. 2017. Adam: A Method for Stochastic Optimization. (2017). arxiv:1412.6980\u00a0[cs.LG]"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Bo Li Ruoming Pang Tara\u00a0N. Sainath Anmol Gulati Yu Zhang James Qin Parisa Haghani W.\u00a0Ronny Huang Min Ma and Junwen Bai. 2021. Scaling End-to-End Models for Large-Scale Multilingual ASR. (2021). arxiv:2104.14830\u00a0[cs.CL]","DOI":"10.1109\/ASRU51503.2021.9687871"},{"key":"e_1_3_2_1_34_1","unstructured":"Hexin Liu Xiangyu Zhang Leibny\u00a0Paola Garcia Andy W.\u00a0H. Khong Eng\u00a0Siong Chng and Shinji Watanabe. 2024. Aligning Speech to Languages to Enhance Code-switching Speech Recognition. https:\/\/api.semanticscholar.org\/CorpusID:268351705"},{"key":"e_1_3_2_1_35_1","unstructured":"Shih-Yang Liu Chien-Yi Wang Hongxu Yin Pavlo Molchanov Yu-Chiang\u00a0Frank Wang Kwang-Ting Cheng and Min-Hung Chen. 2024. DoRA: Weight-Decomposed Low-Rank Adaptation. (2024). arxiv:2402.09353\u00a0[cs.CL]"},{"key":"e_1_3_2_1_36_1","unstructured":"Yun Luo Zhen Yang Fandong Meng Yafu Li Jie Zhou and Yue Zhang. 2023. An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning. (2023). arxiv:2308.08747\u00a0[cs.CL]"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0305000900013866"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-971X.1989.tb00673.x"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.conll-1.46"},{"key":"e_1_3_2_1_40_1","volume-title":"Soumi Maiti, and Shinji Watanabe.","author":"Peng Yifan","year":"2023","unstructured":"Yifan Peng, Jinchuan Tian, Brian Yan, Dan Berrebbi, Xuankai Chang, Xinjian Li, Jiatong Shi, Siddhant Arora, William Chen, Roshan Sharma, Wangyou Zhang, Yui Sudo, Muhammad Shakeel, Jee weon Jung, Soumi Maiti, and Shinji Watanabe. 2023. Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data. (2023). arxiv:2309.13876\u00a0[cs.CL]"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Vineel Pratap Anuroop Sriram Paden Tomasello Awni Hannun Vitaliy Liptchinsky Gabriel Synnaeve and Ronan Collobert. 2020. Massively Multilingual ASR: 50 Languages 1 Model 1 Billion Parameters. (2020). arxiv:2007.03001\u00a0[eess.AS]","DOI":"10.21437\/Interspeech.2020-2831"},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0202)","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Tao Xu, Greg Brockman, Christine Mcleavey, and Ilya Sutskever. 2023. Robust Speech Recognition via Large-Scale Weak Supervision. In Proceedings of the 40th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0202), Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). PMLR, 28492\u201328518. https:\/\/proceedings.mlr.press\/v202\/radford23a.html"},{"key":"e_1_3_2_1_43_1","volume-title":"Teaching the Google Assistant to be multilingual. Google AI Blog","author":"Schalkwyk Johan","year":"2018","unstructured":"Johan Schalkwyk and Ignacio\u00a0Lopez Moreno. 2018. Teaching the Google Assistant to be multilingual. Google AI Blog (2018)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.410"},{"key":"e_1_3_2_1_45_1","unstructured":"Silero Team. 2021. Silero VAD: pre-trained enterprise-grade Voice Activity Detector (VAD) Number Detector and Language Classifier. https:\/\/github.com\/snakers4\/silero-vad."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"J\u00f6rgen Valk and Tanel Alum\u00e4e. 2020. VoxLingua107: a Dataset for Spoken Language Recognition. arxiv:2011.12998\u00a0[eess.AS]","DOI":"10.1109\/SLT48900.2021.9383459"},{"key":"e_1_3_2_1_47_1","volume-title":"The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges. (12","author":"Winata Genta\u00a0Indra","year":"2022","unstructured":"Genta\u00a0Indra Winata, Alham\u00a0Fikri Aji, Zheng-Xin Yong, and Thamar Solorio. 2022. The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges. (12 2022). https:\/\/arxiv.org\/abs\/2212.09660"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379503.3403563"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.10.006"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.calcs-1.5"},{"key":"e_1_3_2_1_51_1","unstructured":"Xianghu Yue Grandee Lee Emre Y\u0131lmaz Fang Deng and Haizhou Li. 2019. End-to-End Code-Switching ASR for Low-Resourced Language Pairs. (2019). arxiv:1909.12681\u00a0[cs.CL]"},{"key":"e_1_3_2_1_52_1","volume-title":"Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv preprint arXiv:2106.10199","author":"Zaken Elad\u00a0Ben","year":"2021","unstructured":"Elad\u00a0Ben Zaken, Shauli Ravfogel, and Yoav Goldberg. 2021. Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv preprint arXiv:2106.10199 (2021)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.774"}],"event":{"name":"CUI '24: ACM Conversational User Interfaces 2024","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"],"location":"Luxembourg Luxembourg","acronym":"CUI '24"},"container-title":["ACM Conversational User Interfaces 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640794.3665579","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3640794.3665579","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:04:50Z","timestamp":1755885890000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3640794.3665579"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,8]]},"references-count":53,"alternative-id":["10.1145\/3640794.3665579","10.1145\/3640794"],"URL":"https:\/\/doi.org\/10.1145\/3640794.3665579","relation":{},"subject":[],"published":{"date-parts":[[2024,7,8]]},"assertion":[{"value":"2024-07-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}