{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T00:56:49Z","timestamp":1781139409900,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T00:00:00Z","timestamp":1717372800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Pulitzer Center"},{"name":"Cornell Center for Social Sciences"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,3]]},"DOI":"10.1145\/3630106.3658996","type":"proceedings-article","created":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T13:14:21Z","timestamp":1717593261000},"page":"1672-1681","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":75,"title":["Careless Whisper: Speech-to-Text Hallucination Harms"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6233-8256","authenticated-orcid":false,"given":"Allison","family":"Koenecke","sequence":"first","affiliation":[{"name":"Cornell University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2482-2713","authenticated-orcid":false,"given":"Anna Seo Gyeong","family":"Choi","sequence":"additional","affiliation":[{"name":"Cornell University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9685-3936","authenticated-orcid":false,"given":"Katelyn X.","family":"Mei","sequence":"additional","affiliation":[{"name":"University of Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0233-6970","authenticated-orcid":false,"given":"Hilke","family":"Schellmann","sequence":"additional","affiliation":[{"name":"New York University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1049-2267","authenticated-orcid":false,"given":"Mona","family":"Sloane","sequence":"additional","affiliation":[{"name":"University of Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,6,5]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Feasibility of automatic speech recognition for providing feedback during tablet-based treatment for apraxia of speech plus aphasia. American journal of speech-language pathology 28, 2S","author":"Ballard J","year":"2019","unstructured":"Kirrie\u00a0J Ballard, Nicole\u00a0M Etter, Songjia Shen, Penelope Monroe, and Chek Tien\u00a0Tan. 2019. Feasibility of automatic speech recognition for providing feedback during tablet-based treatment for apraxia of speech plus aphasia. American journal of speech-language pathology 28, 2S (2019), 818\u2013834."},{"key":"e_1_3_2_1_2_1","volume-title":"Fairness in machine learning. Nips tutorial 1","author":"Barocas Solon","year":"2017","unstructured":"Solon Barocas, Moritz Hardt, and Arvind Narayanan. 2017. Fairness in machine learning. Nips tutorial 1 (2017), 2017."},{"key":"e_1_3_2_1_3_1","volume-title":"Fairness and Machine Learning: Limitations and Opportunities","author":"Barocas Solon","unstructured":"Solon Barocas, Moritz Hardt, and Arvind Narayanan. 2023. Fairness and Machine Learning: Limitations and Opportunities. MIT Press."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780195089349.001.0001","volume-title":"Aphasia: A clinical perspective","author":"Benson David\u00a0Frank","year":"1996","unstructured":"David\u00a0Frank Benson and Alfredo Ardila. 1996. Aphasia: A clinical perspective. Oxford University Press, USA."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-560"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.3109\/17549507.2010.520090"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1056\/nejm199202203260806"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1080\/10749357.2016.1150412"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.2196\/46885"},{"key":"e_1_3_2_1_10_1","volume-title":"Hallucinations in Neural Automatic Speech Recognition: Identifying Errors and Hallucinatory Models. arXiv preprint arXiv:2401.01572","author":"Frieske Rita","year":"2024","unstructured":"Rita Frieske and Bertram\u00a0E Shi. 2024. Hallucinations in Neural Automatic Speech Recognition: Identifying Errors and Hallucinatory Models. arXiv preprint arXiv:2401.01572 (2024)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.4135\/9781849208574"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/s0167-6393(01)00041-3"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1915768117"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.specom.2018.04.001","article-title":"Automatic quantitative analysis of spontaneous aphasic speech","volume":"100","author":"Le Duc","year":"2018","unstructured":"Duc Le, Keli Licata, and Emily\u00a0Mower Provost. 2018. Automatic quantitative analysis of spontaneous aphasic speech. Speech Communication 100 (2018), 1\u201312.","journal-title":"Speech Communication"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-213"},{"key":"e_1_3_2_1_17_1","volume-title":"Does Automatic Speech Recognition (ASR) Have a Role in the Transcription of Indistinct Covert Recordings for Forensic Purposes?Frontiers in Communication 7","author":"Loakes Debbie","year":"2022","unstructured":"Debbie Loakes. 2022. Does Automatic Speech Recognition (ASR) Have a Role in the Transcription of Indistinct Covert Recordings for Forensic Purposes?Frontiers in Communication 7 (2022), 803452."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/ohn.170"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1080\/02687038.2011.589893"},{"key":"e_1_3_2_1_20_1","volume-title":"Transcribing Takes the Next Step.","author":"Markoff John","year":"2019","unstructured":"John Markoff. 2019. From Your Mouth to Your Screen, Transcribing Takes the Next Step. New York Times (October 2019)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Tara McAllister and Kirrie\u00a0J Ballard. 2018. Bringing advanced speech processing technology to the clinical management of speech disorders. 581\u2013582\u00a0pages.","DOI":"10.1080\/17549507.2018.1510034"},{"key":"e_1_3_2_1_22_1","volume-title":"Hackers Can Simply Talk Computers Into Misbehaving. Wall Street Journal (August","author":"McMillan Robert","year":"2023","unstructured":"Robert McMillan. 2023. With AI, Hackers Can Simply Talk Computers Into Misbehaving. Wall Street Journal (August 2023)."},{"key":"e_1_3_2_1_23_1","volume-title":"How Tech Giants Cut Corners to Harvest Data for A.I.New York Times (April","author":"Metz Cade","year":"2024","unstructured":"Cade Metz, Cecilia Kang, Sheera Frenkel, Stuart\u00a0A. Thompson, and Nico Grant. 2024. How Tech Giants Cut Corners to Harvest Data for A.I.New York Times (April 2024)."},{"key":"e_1_3_2_1_24_1","unstructured":"OpenAI. 2023. GPT 3.5. https:\/\/platform.openai.com\/docs\/models\/gpt-3-5. Accessed: 2023-11-25."},{"key":"e_1_3_2_1_25_1","unstructured":"OpenAI. 2023. Speech to text. https:\/\/platform.openai.com\/docs\/guides\/speech-to-text. Accessed: 2023-11-25."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594049"},{"key":"e_1_3_2_1_27_1","volume-title":"Proc. INTERSPEECH","author":"Plaquet Alexis","year":"2023","unstructured":"Alexis Plaquet and Herv\u00e9 Bredin. 2023. Powerset multi-class cross entropy loss for neural speaker diarization. In Proc. INTERSPEECH 2023."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Ying Qin Tan Lee Siyuan Feng and Anthony Pak-Hin Kong. 2018. Automatic Speech Assessment for People with Aphasia Using TDNN-BLSTM with Multi-Task Learning.. In Interspeech. 3418\u20133422.","DOI":"10.21437\/Interspeech.2018-1630"},{"key":"e_1_3_2_1_29_1","volume-title":"Robust Speech Recognition via Large-Scale Weak Supervision. arXiv","author":"Radford Alec","year":"2022","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2022. Robust Speech Recognition via Large-Scale Weak Supervision. arXiv (2022). arXiv:arXiv:2212.04356"},{"key":"e_1_3_2_1_30_1","volume-title":"Bias reduction using Mahalanobis-metric matching. Biometrics","author":"Rubin B","year":"1980","unstructured":"Donald\u00a0B Rubin. 1980. Bias reduction using Mahalanobis-metric matching. Biometrics (1980), 293\u2013298."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2022.3145313"},{"key":"e_1_3_2_1_32_1","volume-title":"prisons mull AI to analyze inmate phone calls","author":"Sherfinski David","year":"2021","unstructured":"David Sherfinski and Avi Asher-Schapiro. 2021. U.S. prisons mull AI to analyze inmate phone calls. Thomson Reuters Foundation News (August 2021)."},{"key":"e_1_3_2_1_33_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_34_1","unstructured":"The New York City Council. 2021. A Local Law to amend the administrative code of the city of New York in relation to automated employment decision tools. https:\/\/www.nyc.gov\/site\/dca\/about\/automated-employment-decision-tools.page."},{"key":"e_1_3_2_1_35_1","unstructured":"US Department of Labor. 1990. Americans with Disabilities Act. https:\/\/www.dol.gov\/general\/topic\/disability\/ada."},{"key":"e_1_3_2_1_36_1","unstructured":"US Equal Employment Opportunity Commission. 2008. The ADA: Your Responsibilities as an Employer. https:\/\/www.eeoc.gov\/publications\/ada-your-responsibilities-employer."},{"key":"e_1_3_2_1_37_1","first-page":"124","article-title":"Automatic Speech Recognition System to Record Progress Notes in a Mobile EHR: A Pilot Study.","volume":"310","author":"Vargas Carolina\u00a0Paula","year":"2024","unstructured":"Carolina\u00a0Paula Vargas, Alejandro Gaiera, Andres Brand\u00e1n, Alejandro Renato, Sonia Benitez, and Daniel Luna. 2024. Automatic Speech Recognition System to Record Progress Notes in a Mobile EHR: A Pilot Study.Studies in Health Technology and Informatics 310 (2024), 124\u2013128.","journal-title":"Studies in Health Technology and Informatics"}],"event":{"name":"FAccT '24: The 2024 ACM Conference on Fairness, Accountability, and Transparency","location":"Rio de Janeiro Brazil","acronym":"FAccT '24"},"container-title":["The 2024 ACM Conference on Fairness, Accountability, and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3630106.3658996","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3630106.3658996","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:50:58Z","timestamp":1750287058000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3630106.3658996"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,3]]},"references-count":37,"alternative-id":["10.1145\/3630106.3658996","10.1145\/3630106"],"URL":"https:\/\/doi.org\/10.1145\/3630106.3658996","relation":{},"subject":[],"published":{"date-parts":[[2024,6,3]]},"assertion":[{"value":"2024-06-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}