{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T01:19:46Z","timestamp":1790299186522,"version":"4.1.0"},"reference-count":37,"publisher":"Wiley","license":[{"start":{"date-parts":[[2024,8,19]],"date-time":"2024-08-19T00:00:00Z","timestamp":1724025600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["The Laryngoscope"],"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>To evaluate the performance of commercial automatic speech recognition (ASR) systems on d\/Deaf and hard\u2010of\u2010hearing (d\/Dhh) speech.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A corpus containing 850 audio files of d\/Dhh and normal hearing (NH) speech from the University of Memphis Speech Perception Assessment Laboratory was tested on four speech\u2010to\u2010text application program interfaces (APIs): Amazon Web Services, Microsoft Azure, Google Chirp, and OpenAI Whisper. We quantified the Word Error Rate (WER) of API transcriptions for 24 d\/Dhh and nine NH participants and performed subgroup analysis by speech intelligibility classification (SIC), hearing loss (HL) onset, and primary communication mode.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Mean WER averaged across APIs was 10 times higher for the d\/Dhh group (52.6%) than the NH group (5.0%). APIs performed significantly worse for \u201clow\u201d and \u201cmedium\u201d SIC (85.9% and 46.6% WER, respectively) as compared to \u201chigh\u201d SIC group (9.5% WER, comparable to NH group). APIs performed significantly worse for speakers with prelingual HL relative to postlingual HL (80.5% and 37.1% WER, respectively). APIs performed significantly worse for speakers primarily communicating with sign language (70.2% WER) relative to speakers with both oral and sign language communication (51.5%) or oral communication only (19.7%).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Commercial ASR systems underperform for d\/Dhh individuals, especially those with \u201clow\u201d and \u201cmedium\u201d SIC, prelingual onset of HL, and sign language as primary communication mode. This contrasts with Big Tech companies' promises of accessibility, indicating the need for ASR systems ethically trained on heterogeneous d\/Dhh speech data.<\/jats:p><\/jats:sec><jats:sec><jats:title>Level of Evidence<\/jats:title><jats:p>3 <jats:italic>Laryngoscope<\/jats:italic>, 2024<\/jats:p><\/jats:sec>","DOI":"10.1002\/lary.31713","type":"journal-article","created":{"date-parts":[[2024,8,19]],"date-time":"2024-08-19T09:59:01Z","timestamp":1724061541000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Quantification of Automatic Speech Recognition System Performance on d\/Deaf and Hard of Hearing Speech"],"prefix":"10.1002","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0345-2756","authenticated-orcid":false,"given":"Robin","family":"Zhao","sequence":"first","affiliation":[{"name":"Sean Parker Institute for the Voice, Weill Cornell Medical College  New York New York U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna S.G.","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Information Science Cornell University  Ithaca New York U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Allison","family":"Koenecke","sequence":"additional","affiliation":[{"name":"Department of Information Science Cornell University  Ithaca New York U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1543-2634","authenticated-orcid":false,"given":"Ana\u00efs","family":"Rameau","sequence":"additional","affiliation":[{"name":"Sean Parker Institute for the Voice, Weill Cornell Medical College  New York New York U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,8,19]]},"reference":[{"key":"e_1_2_6_2_1","doi-asserted-by":"crossref","unstructured":"PapakyriakopoulosO ChoiASG ThongW ZhaoD AndrewsJ BourkeR XiangA KoeneckeA.Augmented Datasheets for Speech Datasets and Ethical Decision\u2010Making. In Proceedings of the 2023 ACM Conference on Fairness Accountability and Transparency (FAccT'23).2023;881\u2013904.","DOI":"10.1145\/3593013.3594049"},{"key":"e_1_2_6_3_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1915768117"},{"key":"e_1_2_6_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/lary.29082"},{"key":"e_1_2_6_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/ohn.170"},{"key":"e_1_2_6_6_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.413278"},{"key":"e_1_2_6_7_1","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.3703.510"},{"key":"e_1_2_6_8_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.400107"},{"key":"e_1_2_6_9_1","doi-asserted-by":"publisher","DOI":"10.1177\/153944920702700305"},{"key":"e_1_2_6_10_1","doi-asserted-by":"publisher","DOI":"10.1177\/104365969901000413"},{"key":"e_1_2_6_11_1","volume-title":"Speech of the Hearing Impaired","author":"Thirumalai MS","year":"2004"},{"key":"e_1_2_6_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-12-608608-9.50013-9"},{"key":"e_1_2_6_13_1","doi-asserted-by":"crossref","unstructured":"GlasserAT KushalnagarKR KushalnagarRS.Feasibility of using automatic speech recognition with voices of deaf and hard\u2010of\u2010hearing individuals. In Proceedings of the 19th International ACM SIGACCESS Conference on Computers and Accessibility.2017:373\u2013374.","DOI":"10.1145\/3132525.3134819"},{"key":"e_1_2_6_14_1","doi-asserted-by":"publisher","DOI":"10.3109\/14992027.2010.549515"},{"key":"e_1_2_6_15_1","doi-asserted-by":"crossref","unstructured":"BanerjeeB KapourchaliMH NajninS MendelLL LeeS PatroC andPoussonM.Inferring hearing loss from learned speech kernels. Proceedings of IEEE International Conference on Machine Learning and Applications2016:26\u201331.","DOI":"10.1109\/ICMLA.2016.0014"},{"key":"e_1_2_6_16_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.4994288"},{"key":"e_1_2_6_17_1","unstructured":"Accessed April 14 2024.https:\/\/translator.microsoft.com\/"},{"key":"e_1_2_6_18_1","unstructured":"Accessed April 14 2024.https:\/\/www.microsoft.com\/en-us\/translator\/APPS\/PRESENTATION-TRANSLATOR\/"},{"key":"e_1_2_6_19_1","unstructured":"Accessed April 14 2024.https:\/\/www.ibm.com\/products\/speech-to-text"},{"key":"e_1_2_6_20_1","doi-asserted-by":"crossref","unstructured":"Glasser A.Automatic speech recognition services: Deaf and hard\u2010of\u2010hearing usability. In Extended abstracts of the 2019 CHI conference on human factors in computing systems.2019:1\u20136.","DOI":"10.1145\/3290607.3308461"},{"key":"e_1_2_6_21_1","doi-asserted-by":"crossref","unstructured":"ChangX YanB ChoiK et al.Exploring speech recognition translation and understanding with discrete speech units: A comparative study. ICASSP 2024\u20132024 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP).2024https:\/\/doi.org\/10.1109\/icassp48485.2024.10447929.","DOI":"10.1109\/ICASSP48485.2024.10447929"},{"key":"e_1_2_6_22_1","doi-asserted-by":"publisher","DOI":"10.2307\/2529981"},{"key":"e_1_2_6_23_1","doi-asserted-by":"publisher","DOI":"10.1044\/1058-0360(2003\/090)"},{"key":"e_1_2_6_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijporl.2003.11.006"},{"key":"e_1_2_6_25_1","doi-asserted-by":"publisher","DOI":"10.1097\/AUD.0b013e3181a165be"},{"key":"e_1_2_6_26_1","doi-asserted-by":"publisher","DOI":"10.1097\/AUD.0b013e3182587356"},{"key":"e_1_2_6_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejenta.2013.06.003"},{"issue":"5","key":"e_1_2_6_28_1","doi-asserted-by":"crossref","first-page":"724","DOI":"10.1016\/j.amjoto.2019.06.011","article-title":"The effectiveness of cognitive rehabilitation program on auditory perception and verbal intelligibility of deaf children","volume":"40","author":"Ashori M","year":"2019","journal-title":"Am J Otolaryngol"},{"key":"e_1_2_6_29_1","doi-asserted-by":"publisher","DOI":"10.1097\/01.AUD.0000051689.57380.1B"},{"key":"e_1_2_6_30_1","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.2603.451"},{"key":"e_1_2_6_31_1","unstructured":"RadfordA KimJW XuT BrockmanG McLeaveyC SutskeverI.Robust speech recognition via large\u2010scale weak supervision. In International Conference on Machine Learning.2023:28492\u201328518.https:\/\/doi.org\/10.48550\/arXiv.2212.04356"},{"key":"e_1_2_6_32_1","doi-asserted-by":"crossref","unstructured":"KoeneckeA ChoiASG MeiK SchellmannH SloaneM.Careless Whisper: Speech\u2010to\u2010Text Hallucination Harms. In Proceedings of the 2024 ACM Conference on Fairness Accountability and Transparency (FAccT'24).2024;1672\u20131681.","DOI":"10.1145\/3630106.3658996"},{"key":"e_1_2_6_33_1","doi-asserted-by":"crossref","unstructured":"TomanekK TobinJ VenugopalanS CaveR SeaverK GreenJR HeywoodR.Large Language Models As A Proxy For Human Evaluation In Assessing The Comprehensibility Of Disordered Speech Transcription. In ICASSP 2024\u20102024 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP).2024;10846\u201310850.https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10447177","DOI":"10.1109\/ICASSP48485.2024.10447177"},{"key":"e_1_2_6_34_1","unstructured":"Project Euphoria. Accessed April 14 2024.https:\/\/sites.research.google\/euphonia\/about\/"},{"key":"e_1_2_6_35_1","unstructured":"CattiauJ.A communication tool for people with non\u2010standard speech.2022.https:\/\/blog.google\/outreach-initiatives\/accessibility\/project-relate\/."},{"key":"e_1_2_6_36_1","unstructured":"2019 NTID Annual Report final. Accessed April 14 2024.https:\/\/www.rit.edu\/ntid\/sites\/rit.edu.ntid\/files\/aboutntid\/annual_report_2019.pdf"},{"key":"e_1_2_6_37_1","unstructured":"2007 NTID Annual Report. Accessed April 14 2024.https:\/\/www.rit.edu\/ntid\/sites\/rit.edu.ntid\/files\/aboutntid\/annual_report2007.pdf"},{"key":"e_1_2_6_38_1","doi-asserted-by":"crossref","unstructured":"FuruiS NakamuraM IchibaT IwanoK.Why is the recognition of spontaneous speech so hard? Text speech and dialogue.2005:9\u201322.https:\/\/doi.org\/10.1007\/11551874_3","DOI":"10.1007\/11551874_3"}],"container-title":["The Laryngoscope"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/lary.31713","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,19]],"date-time":"2024-08-19T09:59:11Z","timestamp":1724061551000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/lary.31713"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,19]]},"references-count":37,"alternative-id":["10.1002\/lary.31713"],"URL":"https:\/\/doi.org\/10.1002\/lary.31713","archive":["Portico"],"relation":{},"ISSN":["0023-852X","1531-4995"],"issn-type":[{"value":"0023-852X","type":"print"},{"value":"1531-4995","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,19]]},"assertion":[{"value":"2024-04-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-07-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"lary.31713"}}