{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T03:34:56Z","timestamp":1777952096863,"version":"3.51.4"},"reference-count":32,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":31,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Procedia Computer Science"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1016\/j.procs.2026.01.080","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T19:30:19Z","timestamp":1774035019000},"page":"692-699","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Measuring linguistic bias in ASR: Whisper large-v3 on non-native speech versus human perception"],"prefix":"10.1016","volume":"275","author":[{"given":"Elsayed","family":"Issa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahmoud","family":"Ali","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Hirschi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.procs.2026.01.080_bib1","doi-asserted-by":"crossref","unstructured":"Ali, M.M.E., 2023. The foreign-accentedness, comprehensibility, and intelligibility of l2 arabic speech. Language Teaching Research 0. doi: 10.1177\/13621688231158787.","DOI":"10.1177\/13621688231158787"},{"key":"10.1016\/j.procs.2026.01.080_bib2","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.csl.2009.04.005","article-title":"Study on pharyngeal and uvular consonants in foreign accented arabic for asr","volume":"24","author":"Alotaibi","year":"2010","journal-title":"Computer Speech & Language"},{"key":"10.1016\/j.procs.2026.01.080_bib3","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1007\/s10579-020-09505-5","article-title":"Investigating the effects of gender, dialect, and training size on the performance of arabic speech recognition","volume":"54","author":"Alsharhan","year":"2020","journal-title":"Language Resources and Evaluation"},{"key":"10.1016\/j.procs.2026.01.080_bib4","doi-asserted-by":"crossref","first-page":"3958","DOI":"10.21105\/joss.03958","article-title":"Phonemizer: Text to phones transcription for multiple languages in python","volume":"6","author":"Bernard","year":"2021","journal-title":"Journal of Open Source Software"},{"key":"10.1016\/j.procs.2026.01.080_bib5","doi-asserted-by":"crossref","unstructured":"Chan, M.P.Y., Choe, J., Li, A., Chen, Y., Gao, X., Holliday, N., 2022. Training and typological bias in asr performance for world englishes, in:Proceedings of Interspeech 2022, pp. 1273\u20131277. doi: 10.21437\/Interspeech.2022-10869.","DOI":"10.21437\/Interspeech.2022-10869"},{"key":"10.1016\/j.procs.2026.01.080_bib6","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1017\/S0272263125000014","article-title":"The relationships among l2 fluency, intelligibility, comprehensibility, and accentedness: A meta-analysis","volume":"47","author":"Chau","year":"2025","journal-title":"Studies in Second Language Acquisition"},{"key":"10.1016\/j.procs.2026.01.080_bib7","doi-asserted-by":"crossref","unstructured":"Crowther, D., Isbell, D.R., Kim, Y., Kim, J., 2025. The relationship between intelligibility and comprehensibility in second language speech. Bilingualism: Language and Cognition, 1\u20137doi: https:\/\/doi.org\/10.1017\/S1366728925100606.","DOI":"10.1017\/S1366728925100606"},{"key":"10.1016\/j.procs.2026.01.080_bib8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1017\/S0272263197001010","article-title":"Accent, intelligibility, and comprehensibility: Evidence from four l1s","volume":"19","author":"Derwing","year":"1997","journal-title":"Studies in second language acquisition"},{"key":"10.1016\/j.procs.2026.01.080_bib9","doi-asserted-by":"crossref","first-page":"101567","DOI":"10.1016\/j.csl.2023.101567","article-title":"Towards inclusive automatic speech recognition","volume":"84","author":"Feng","year":"2024","journal-title":"Computer Speech & Language"},{"key":"10.1016\/j.procs.2026.01.080_bib10","unstructured":"Feng, S., Kudina, O., Halpern, B.M., Scharenborg, O., 2021. Quantifying bias in automatic speech recognition. arXiv preprint arXiv:2103.15122."},{"key":"10.1016\/j.procs.2026.01.080_bib11","doi-asserted-by":"crossref","first-page":"3125","DOI":"10.1121\/1.413041","article-title":"Factors affecting strength of perceived foreign accent in a second language","volume":"97","author":"Flege","year":"1995","journal-title":"The Journal of the Acoustical Society of America"},{"key":"10.1016\/j.procs.2026.01.080_bib12","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1111\/lang.12448","article-title":"(generalized linear) mixed-effects modeling: A learner corpus example","volume":"71","author":"Gries","year":"2021","journal-title":"Language Learning"},{"key":"10.1016\/j.procs.2026.01.080_bib13","series-title":"Modern standard Arabic phonetics for speech synthesis. Ph.D. thesis","author":"Halabi","year":"2016"},{"key":"10.1016\/j.procs.2026.01.080_bib14","doi-asserted-by":"crossref","first-page":"101278","DOI":"10.1016\/j.csl.2021.101278","article-title":"Investigations on speech recognition systems for low-resource dialectal arabic\u2013english code-switching speech","volume":"72","author":"Hamed","year":"2022","journal-title":"Computer Speech & Language"},{"key":"10.1016\/j.procs.2026.01.080_bib15","series-title":"Dharma: residual diagnostics for hierarchical (multi-level\/mixed) regression models","author":"Hartig","year":"2016"},{"key":"10.1016\/j.procs.2026.01.080_bib16","unstructured":"Hinsvark, A., Delworth, N., Del Rio, M., McNamara, Q., Dong, J., Westerman, R., Huang, M., Palakapilly, J., Drexler, J., Pirkin, I., et al., 2021. Accented speech recognition: A survey. arXiv preprint arXiv:2104.10747."},{"key":"10.1016\/j.procs.2026.01.080_bib17","doi-asserted-by":"crossref","first-page":"1575","DOI":"10.1111\/ijal.12580","article-title":"Linguistic influences on comprehensibility and accentedness in second language korean speech","volume":"34","author":"Isbell","year":"2024","journal-title":"International Journal of Applied Linguistics"},{"key":"10.1016\/j.procs.2026.01.080_bib18","doi-asserted-by":"crossref","unstructured":"Keleg, A., Goldwater, S., Magdy, W., 2023. Aldi: Quantifying the arabic level of dialectness of text, in: The 2023 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics. pp. 10597\u201310611. doi: 10.18653\/v1\/2023.emnlp-main.655.","DOI":"10.18653\/v1\/2023.emnlp-main.655"},{"key":"10.1016\/j.procs.2026.01.080_bib19","doi-asserted-by":"crossref","first-page":"7684","DOI":"10.1073\/pnas.1915768117","article-title":"Racial disparities in automated speech recognition","volume":"117","author":"Koenecke","year":"2020","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"10.1016\/j.procs.2026.01.080_bib20","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1093\/applin\/amac066","article-title":"Bias in automatic speech recognition: The case of african american language","volume":"44","author":"Martin","year":"2023","journal-title":"Applied Linguistics"},{"key":"10.1016\/j.procs.2026.01.080_bib21","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1075\/jslp.1.1.01mun","article-title":"A prospectus for pronunciation research in the 21st century: A point of view","volume":"1","author":"Munro","year":"2015","journal-title":"Journal of Second Language Pronunciation"},{"key":"10.1016\/j.procs.2026.01.080_bib22","doi-asserted-by":"crossref","first-page":"4734","DOI":"10.3390\/app14114734","article-title":"Gender and accent biases in ai-based tools for spanish: A comparative study between alexa and whisper","volume":"14","author":"Nacimiento-Garc\u00eda","year":"2024","journal-title":"Applied Sciences"},{"key":"10.1016\/j.procs.2026.01.080_bib23","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1075\/jslp.20009.nag","article-title":"Expanding the scope of l2 intelligibility research: Intelligibility, comprehensibility, and accentedness in l2 spanish","volume":"6","author":"Nagle","year":"2020","journal-title":"Journal of Second Language Pronunciation"},{"key":"10.1016\/j.procs.2026.01.080_bib24","doi-asserted-by":"crossref","unstructured":"Nahar, K.M.O., Elshafei, M., Al-Khatib, W.G., Al-Muhtaseb, H., Alghamdi, M.M., 2012. Statistical analysis of arabic phonemes used in arabic speech recognition, in: International Conference on Neural Information Processing, Springer. pp. 533\u2013542. doi: 10.1007\/978-3-642-34475-6_64.","DOI":"10.1007\/978-3-642-34475-6_64"},{"key":"10.1016\/j.procs.2026.01.080_bib25","doi-asserted-by":"crossref","unstructured":"Prasad, A., Jyothi, P., 2020. How accents confound: Probing for accent information in end-to-end speech recognition systems, in: Proceedings of the 58th annual meeting of the association for computational linguistics, pp. 3739\u20133753. doi: 10.18653\/v1\/2020.acl-main.345.","DOI":"10.18653\/v1\/2020.acl-main.345"},{"key":"10.1016\/j.procs.2026.01.080_bib26","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I., 2023. Robust speech recognition via large-scale weak supervision, in: International Conference on Machine Learning, PMLR. pp. 28492\u201328518."},{"key":"10.1016\/j.procs.2026.01.080_bib27","doi-asserted-by":"crossref","unstructured":"Rice, K., 2007. Markedness in phonology. The Cambridge handbook of phonology, 79\u201397doi: 10.1017\/CBO9780511486371.005.","DOI":"10.1017\/CBO9780511486371.005"},{"key":"10.1016\/j.procs.2026.01.080_bib28","unstructured":"Sawalha, M., Abu Shariah, M., 2013. The effects of speakers\u2019 gender, age, and region on overall performance of arabic automatic speech recognition systems using the phonetically rich and balanced modern standard arabic speech corpus, in: Proceedings of the 2nd Workshop of Arabic Corpus Linguistics (WACL-2). 2nd Workshop of Arabic Corpus Linguistics WACL-2."},{"key":"10.1016\/j.procs.2026.01.080_bib29","doi-asserted-by":"crossref","unstructured":"Talafha, B., Waheed, A., Abdul-Mageed, M., 2023. N-shot benchmarking of whisper on diverse arabic speech recognition. arXiv preprint arXiv:2306.02902.","DOI":"10.21437\/Interspeech.2023-1044"},{"key":"10.1016\/j.procs.2026.01.080_bib30","doi-asserted-by":"crossref","unstructured":"Tatman, R., 2017. Gender and dialect bias in youtube\u2019s automatic captions, in: Proceedings of the First ACL Workshop on Ethics in Natural Language Processing, pp. 53\u201359. doi: 10.18653\/v1\/W17-1606.","DOI":"10.18653\/v1\/W17-1606"},{"key":"10.1016\/j.procs.2026.01.080_bib31","doi-asserted-by":"crossref","unstructured":"Tatman, R., Kasten, C., 2017. Efects of talker dialect, gender & race on accuracy of bing speech and youtube automatic captions, in: Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH 2017), pp. 934\u2013938. doi: 10. 21437\/Interspeech.2017-1746.","DOI":"10.21437\/Interspeech.2017-1746"},{"key":"10.1016\/j.procs.2026.01.080_bib32","doi-asserted-by":"crossref","first-page":"905","DOI":"10.1017\/S1366728912000168","article-title":"Disentangling accent from comprehensibility","volume":"15","author":"Trofmovich","year":"2012","journal-title":"Bilingualism: Language and cognition"}],"container-title":["Procedia Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877050926000803?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877050926000803?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T11:30:37Z","timestamp":1777894237000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1877050926000803"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":32,"alternative-id":["S1877050926000803"],"URL":"https:\/\/doi.org\/10.1016\/j.procs.2026.01.080","relation":{},"ISSN":["1877-0509"],"issn-type":[{"value":"1877-0509","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Measuring linguistic bias in ASR: Whisper large-v3 on non-native speech versus human perception","name":"articletitle","label":"Article Title"},{"value":"Procedia Computer Science","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.procs.2026.01.080","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}]}}