{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T00:57:29Z","timestamp":1781139449743,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,19]],"date-time":"2023-04-19T00:00:00Z","timestamp":1681862400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,19]]},"DOI":"10.1145\/3544548.3581385","type":"proceedings-article","created":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T04:26:08Z","timestamp":1681964768000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Situating Automatic Speech Recognition Development within Communities of Under-heard Language Speakers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2078-6699","authenticated-orcid":false,"given":"Thomas","family":"Reitmaier","sequence":"first","affiliation":[{"name":"Swansea University, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4113-2352","authenticated-orcid":false,"given":"Electra","family":"Wallington","sequence":"additional","affiliation":[{"name":"University of Edinburgh, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5495-967X","authenticated-orcid":false,"given":"Ond\u0159ej","family":"Klejch","sequence":"additional","affiliation":[{"name":"University of Edinburgh, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9906-9961","authenticated-orcid":false,"given":"Nina","family":"Markl","sequence":"additional","affiliation":[{"name":"University of Edinburgh, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8474-5098","authenticated-orcid":false,"given":"L\u00e9a-Marie","family":"Lam-Yee-Mui","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Paris-Saclay, CNRS, Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique, France and Vocapia Research, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1960-1012","authenticated-orcid":false,"given":"Jennifer","family":"Pearson","sequence":"additional","affiliation":[{"name":"Swansea University, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7657-7373","authenticated-orcid":false,"given":"Matt","family":"Jones","sequence":"additional","affiliation":[{"name":"Swansea University, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9597-9615","authenticated-orcid":false,"given":"Peter","family":"Bell","sequence":"additional","affiliation":[{"name":"School of Informatics, University of Edinburgh, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9228-006X","authenticated-orcid":false,"given":"Simon","family":"Robinson","sequence":"additional","affiliation":[{"name":"Swansea University, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,4,19]]},"reference":[{"key":"e_1_3_3_3_1_1","volume-title":"Proceedings of the 12th Language Resources and Evaluation Conference. European Language Resources Association","author":"Abraham Basil","year":"2020","unstructured":"Basil Abraham, Danish Goel, Divya Siddarth, Kalika Bali, Manu Chopra, Monojit Choudhury, Pratik Joshi, Preethi Jyoti, Sunayana Sitaram, and Vivek Seshadri. 2020. Crowdsourcing Speech Data for Low-Resource Languages from Low-Income Workers. In Proceedings of the 12th Language Resources and Evaluation Conference. European Language Resources Association, Marseille, France, 2819\u20132826."},{"key":"e_1_3_3_3_2_1","volume-title":"A Framework for Self-Supervised Learning of Speech Representations. arXiv:2006.11477 [cs, eess] (Oct","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski, Henry Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. Wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. arXiv:2006.11477 [cs, eess] (Oct. 2020). arxiv:2006.11477\u00a0[cs, eess]"},{"key":"e_1_3_3_3_3_1","volume-title":"The NCHLT Speech Corpus of the South African Languages. In 4th International Workshop on Spoken Language Technologies for Under-Resourced Languages","author":"Barnard E.","unstructured":"E. Barnard, M.\u00a0H. Davel, C. Van\u00a0Heerden, Febe De\u00a0Wet, and J. Badenhorst. 2014. The NCHLT Speech Corpus of the South African Languages. In 4th International Workshop on Spoken Language Technologies for Under-Resourced Languages. St Petersburg, Russia."},{"key":"e_1_3_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404863"},{"key":"e_1_3_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_3_3_7_1","volume-title":"Thomas Niesler, and Febe de Wet.","author":"Biswas Astik","year":"2018","unstructured":"Astik Biswas, Ewald van\u00a0der Westhuizen, Thomas Niesler, and Febe de Wet. 2018. Improving ASR for Code-Switched Speech in Under-Resourced Languages Using Out-of-Domain Data.. In SLTU. 122\u2013126."},{"key":"e_1_3_3_3_8_1","volume-title":"Bowker and Susan\u00a0Leigh Star","author":"C.","year":"1999","unstructured":"Geoffrey\u00a0C. Bowker and Susan\u00a0Leigh Star. 1999. Sorting Things out: Classification and Its Consequences. MIT Press, Cambridge, Mass."},{"key":"e_1_3_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-2166(99)00094-6"},{"key":"e_1_3_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/1866696.1866697"},{"key":"e_1_3_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300611"},{"key":"e_1_3_3_3_12_1","volume-title":"M\u0101ori Are Trying to Save Their Language from Big Tech. Wired UK (April","author":"Coffey Donavyn","year":"2021","unstructured":"Donavyn Coffey. 2021. M\u0101ori Are Trying to Save Their Language from Big Tech. Wired UK (April 2021)."},{"key":"e_1_3_3_3_13_1","doi-asserted-by":"crossref","unstructured":"Alexis Conneau Alexei Baevski Ronan Collobert Abdelrahman Mohamed and Michael Auli. 2020. Unsupervised cross-lingual representation learning for speech recognition. arXiv preprint arXiv:2006.13979(2020).","DOI":"10.21437\/Interspeech.2021-329"},{"key":"e_1_3_3_3_14_1","volume-title":"Atlas of AI: Power, Politics, and the Planetary Costs of Artificial Intelligence","author":"Crawford Kate","unstructured":"Kate Crawford. 2021. Atlas of AI: Power, Politics, and the Planetary Costs of Artificial Intelligence. Yale University Press, New Haven."},{"key":"e_1_3_3_3_15_1","volume-title":"Language in Public Spaces: Language Choice in Two IsiXhosa Speaking Communities (Langa and Khayelitsha). Ph.\u00a0D. Dissertation","author":"Dantile Andiswa\u00a0Mesatywa","unstructured":"Andiswa\u00a0Mesatywa Dantile. 2015. Language in Public Spaces: Language Choice in Two IsiXhosa Speaking Communities (Langa and Khayelitsha). Ph.\u00a0D. Dissertation. University of Stellenbosch, Stellenbosch, South Africa."},{"key":"e_1_3_3_3_16_1","volume-title":"Izolo: Mobile Diaries of the Less Connected","author":"de Lanerolle Indra","year":"2017","unstructured":"Indra de Lanerolle, Marion Walton, and Alette Schoon. 2017. Izolo: Mobile Diaries of the Less Connected. The Institute of Development Studies, Brighton."},{"key":"e_1_3_3_3_17_1","volume-title":"Woefzela - An Open-Source Platform for ASR Data Collection in the Developing World. (Aug","author":"De\u00a0Vries J.","year":"2011","unstructured":"N.\u00a0J. De\u00a0Vries, J. Badenhorst, M.\u00a0H. Davel, E. Barnard, and A. De\u00a0Waal. 2011. Woefzela - An Open-Source Platform for ASR Data Collection in the Developing World. (Aug. 2011)."},{"key":"e_1_3_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1515\/mult.2010.012"},{"key":"e_1_3_3_3_19_1","volume-title":"Sociolinguistics and Mobile Communication","author":"Deumert Ana","unstructured":"Ana Deumert. 2014. Sociolinguistics and Mobile Communication. Edinburgh University Press, Edinburgh."},{"key":"e_1_3_3_3_20_1","doi-asserted-by":"crossref","unstructured":"Anuj Diwan Rakesh Vaideeswaran Sanket Shah Ankita Singh Srinivasa Raghavan Shreya Khare Vinit Unni Saurabh Vyas Akash Rajpuria Chiranjeevi Yarra 2021. Multilingual and code-switching ASR challenges for low resource Indian languages. arXiv preprint arXiv:2104.00235(2021).","DOI":"10.21437\/Interspeech.2021-1339"},{"key":"e_1_3_3_3_21_1","unstructured":"Vittoria Elliott and Bopha Phorn. 2021. Fifty Percent of Facebook Messenger\u2019s Total Voice Traffic Comes from Cambodia. Here\u2019s Why. https:\/\/restofworld.org\/2021\/facebook-didnt-know-why-half-of-messengers-voice-traffic-comes-from-cambodia-heres-why\/."},{"key":"e_1_3_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordjournals.afraf.a098185"},{"key":"e_1_3_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-610"},{"key":"e_1_3_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9481.00052"},{"key":"e_1_3_3_3_25_1","volume-title":"Papane","author":"Anciano Fiona","year":"2020","unstructured":"Fiona Anciano, SJ Cooper-Knock, Mmeli Dube, Mfundo Majola, and Boitumelo M. Papane. 2020. Cape Town Lockdown Diaries. https:\/\/capetownlockdown.wordpress.com\/."},{"key":"e_1_3_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1093\/llc"},{"key":"e_1_3_3_3_27_1","volume-title":"Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC\u201916)","author":"Gamb\u00e4ck Bj\u00f6rn","year":"2016","unstructured":"Bj\u00f6rn Gamb\u00e4ck and Amitava Das. 2016. Comparing the level of code-switching in corpora. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC\u201916). 1850\u20131855."},{"key":"e_1_3_3_3_28_1","article-title":"Stochastic Parrots: How NLP Research Has Gotten Too Big","volume":"24","author":"Garc\u00eda Esther\u00a0S\u00e1nchez","year":"2021","unstructured":"Esther\u00a0S\u00e1nchez Garc\u00eda and Michael Gasser. 2021. Stochastic Parrots: How NLP Research Has Gotten Too Big. Science for the People Magazine 24, 2 (2021).","journal-title":"Science for the People Magazine"},{"key":"e_1_3_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2677199.2680588"},{"key":"e_1_3_3_3_30_1","volume-title":"Gray and Siddharth Suri","author":"L.","year":"2019","unstructured":"Mary\u00a0L. Gray and Siddharth Suri. 2019. Ghost Work: How to Stop Silicon Valley from Building a New Global Underclass. Houghton Mifflin Harcourt, Boston."},{"key":"e_1_3_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-5802"},{"key":"e_1_3_3_3_32_1","doi-asserted-by":"publisher","DOI":"10.1515\/lingvan-2021-0053"},{"key":"e_1_3_3_3_33_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-551"},{"key":"e_1_3_3_3_34_1","doi-asserted-by":"crossref","unstructured":"Christiaan Jacobs and Herman Kamper. 2021. Multilingual transfer of acoustic word embeddings improves when training on languages related to the target zero-resource language. arXiv preprint arXiv:2106.12834(2021).","DOI":"10.21437\/Interspeech.2021-461"},{"key":"e_1_3_3_3_35_1","doi-asserted-by":"publisher","unstructured":"Pratik Joshi Christain Barnes Sebastin Santy Simran Khanuja Sanket Shah Anirudh Srinivasan Satwik Bhattamishra Sunayana Sitaram Monojit Choudhury and Kalika Bali. 2019. Unsung Challenges of Building and Deploying Language Technologies for Low Resource Language Communities. https:\/\/doi.org\/10.48550\/arXiv.1912.03457 arxiv:1912.03457\u00a0[cs]","DOI":"10.48550\/arXiv.1912.03457"},{"key":"e_1_3_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300389"},{"key":"e_1_3_3_3_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2008.207"},{"key":"e_1_3_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9481.00163"},{"key":"e_1_3_3_3_39_1","volume-title":"Artificial Intelligence: A Guide for Thinking Humans","author":"Mitchell Melanie","year":"2019","unstructured":"Melanie Mitchell. 2019. Artificial Intelligence: A Guide for Thinking Humans. Pelican Books, London."},{"key":"e_1_3_3_3_40_1","doi-asserted-by":"crossref","unstructured":"Andrew\u00a0C Morris Viktoria Maier and Phil Green. 2004. From WER and RIL to MER and WIL : improved evaluation measures for connected speech recognition. In INTERSPEECH-2004. 2765\u20132768.","DOI":"10.21437\/Interspeech.2004-668"},{"key":"e_1_3_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2021.100336"},{"key":"e_1_3_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300326"},{"key":"e_1_3_3_3_43_1","volume-title":"IEEE 2011 workshop on automatic speech recognition and understanding. IEEE Signal Processing Society.","author":"Povey Daniel","year":"2011","unstructured":"Daniel Povey, Arnab Ghoshal, Gilles Boulianne, Lukas Burget, Ondrej Glembek, Nagendra Goel, Mirko Hannemann, Petr Motlicek, Yanmin Qian, Petr Schwarz, 2011. The Kaldi speech recognition toolkit. In IEEE 2011 workshop on automatic speech recognition and understanding. IEEE Signal Processing Society."},{"key":"e_1_3_3_3_44_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1139"},{"key":"e_1_3_3_3_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517639"},{"key":"e_1_3_3_3_46_1","volume-title":"Changing the World by Changing the Data. arXiv:2105.13947 [cs] (May","author":"Rogers Anna","year":"2021","unstructured":"Anna Rogers. 2021. Changing the World by Changing the Data. arXiv:2105.13947 [cs] (May 2021). arxiv:2105.13947\u00a0[cs]"},{"key":"e_1_3_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.2200\/S00418ED1V01Y201205HCI014"},{"key":"e_1_3_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/1753326.1753718"},{"key":"e_1_3_3_3_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445518"},{"key":"e_1_3_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2998581.2998592"},{"key":"e_1_3_3_3_51_1","volume-title":"The Cost of Training NLP Models: A Concise Overview. arXiv:2004.08900 [cs] (April","author":"Sharir Or","year":"2020","unstructured":"Or Sharir, Barak Peleg, and Yoav Shoham. 2020. The Cost of Training NLP Models: A Concise Overview. arXiv:2004.08900 [cs] (April 2020). arxiv:2004.08900\u00a0[cs]"},{"key":"e_1_3_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1515\/lingvan-2021-0051"},{"key":"e_1_3_3_3_53_1","doi-asserted-by":"publisher","DOI":"10.1080\/15710882.2017.1310904"},{"key":"e_1_3_3_3_54_1","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC","author":"van der Westhuizen Ewald","year":"2018","unstructured":"Ewald van der Westhuizen and Thomas Niesler. 2018. 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 2018). European Language Resources Association (ELRA), Miyazaki, Japan."},{"key":"e_1_3_3_3_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2018.10.002"},{"key":"e_1_3_3_3_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300399"},{"key":"e_1_3_3_3_57_1","volume-title":"Crowd-powered Speech Transcription System. In Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery","author":"Vashistha Aditya","year":"2017","unstructured":"Aditya Vashistha, Pooja Sethi, and Richard Anderson. 2017. Respeak: A Voice-based, Crowd-powered Speech Transcription System. In Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, New York, NY, USA, 1855\u20131866."},{"key":"e_1_3_3_3_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173631"},{"key":"e_1_3_3_3_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3129416.3129446"},{"key":"e_1_3_3_3_60_1","volume-title":"Pavement Internet: Mobile Media Economies and Ecologies for Young People in South Africa","author":"Walton Marion","year":"2014","unstructured":"Marion Walton. 2014. Pavement Internet: Mobile Media Economies and Ecologies for Young People in South Africa. In The Routledge Companion to Mobile Media, G.\u00a0Goggin and Larissa Hjorth (Eds.). Routledge, London, UK."},{"key":"e_1_3_3_3_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2008.4777825"},{"key":"e_1_3_3_3_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/2750858.2804249"},{"key":"e_1_3_3_3_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3311957.3359447"}],"event":{"name":"CHI '23: CHI Conference on Human Factors in Computing Systems","location":"Hamburg Germany","acronym":"CHI '23","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3544548.3581385","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3544548.3581385","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:31Z","timestamp":1750178851000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3544548.3581385"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,19]]},"references-count":63,"alternative-id":["10.1145\/3544548.3581385","10.1145\/3544548"],"URL":"https:\/\/doi.org\/10.1145\/3544548.3581385","relation":{},"subject":[],"published":{"date-parts":[[2023,4,19]]},"assertion":[{"value":"2023-04-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}