{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:29:39Z","timestamp":1776889779891,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T00:00:00Z","timestamp":1655683200000},"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":[[2022,6,21]]},"DOI":"10.1145\/3531146.3533089","type":"proceedings-article","created":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T14:27:10Z","timestamp":1655735230000},"page":"230-247","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":39,"title":["Bias in Automated Speaker Recognition"],"prefix":"10.1145","author":[{"given":"Wiebke Toussaint","family":"Hutiri","sequence":"first","affiliation":[{"name":"Technology, Policy & Management \/ Engineering Systems & Services \/ Cyber Physical Intelligence Lab, Delft University of Technology, Netherlands"}]},{"given":"Aaron Yi","family":"Ding","sequence":"additional","affiliation":[{"name":"Technology, Policy & Management\/Engineering Systems & Services \/ Cyber Physical Intelligence Lab, Delft University of Technology, Netherlands"}]}],"member":"320","published-online":{"date-parts":[[2022,6,20]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Do speech recognizers prefer female speakers?INTERSPEECH","author":"Adda-Decker Martine","year":"2005","unstructured":"Martine Adda-Decker and Lori Lamel. 2005. Do speech recognizers prefer female speakers?INTERSPEECH (2005), 2205\u20132208. https:\/\/www.isca-speech.org\/archive\/interspeech_2005\/addadecker05_interspeech.html"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.004"},{"key":"e_1_3_2_1_3_1","volume-title":"Debiasing Word Embeddings. In NIPS\u201916: Proceedings of the 30th International Conference on Neural Information Processing Systems. 4356 \u2013 4364","author":"Bolukbasi Tolga","year":"2016","unstructured":"Tolga Bolukbasi, Kai-wei Chang, James Zou, Venkatesh Saligrama, and Adam Kalai. 2016. Man is to Computer Programmer as Woman is to Homemaker ? Debiasing Word Embeddings. In NIPS\u201916: Proceedings of the 30th International Conference on Neural Information Processing Systems. 4356 \u2013 4364."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of Machine Learning Research: Conference on Fairness, Accountability, and Transparency, Vol.\u00a081","author":"Buolamwini Joy","year":"2018","unstructured":"Joy Buolamwini and Timnit Gebru. 2018. Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification. In Proceedings of Machine Learning Research: Conference on Fairness, Accountability, and Transparency, Vol.\u00a081. 1889\u20131896."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","unstructured":"Joon\u00a0Son Chung and Andrew Zisserman. 2017. Out of time: Automated lip sync in the wild. Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics) 10117 LNCS i(2017) 251\u2013263. https:\/\/doi.org\/10.1007\/978-3-319-54427-4_19","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"e_1_3_2_1_7_1","volume-title":"Fair Voice Biometrics : Impact of Demographic Imbalance on Group Fairness in Speaker Recognition. (2021)","author":"Fenu Gianni","year":"1892","unstructured":"Gianni Fenu, Mirko Marras, Giacomo Medda, and Giacomo Meloni. 2021. Fair Voice Biometrics : Impact of Demographic Imbalance on Group Fairness in Speaker Recognition. (2021), 1892\u20131896."},{"key":"e_1_3_2_1_8_1","volume-title":"An Overview of Speaker Recognition Technology. In ESCA Workshop on Automatic Speaker Recognition, Identification and Verification. 1 \u2013 9.","author":"Furui Sadaoki","year":"1994","unstructured":"Sadaoki Furui. 1994. An Overview of Speaker Recognition Technology. In ESCA Workshop on Automatic Speaker Recognition, Identification and Verification. 1 \u2013 9."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101032"},{"key":"e_1_3_2_1_10_1","volume-title":"The VoxCeleb Speaker Recognition Challenge","author":"Oxford Visual\u00a0Geometry Group","year":"2021","unstructured":"Oxford Visual\u00a0Geometry Group. 2021. The VoxCeleb Speaker Recognition Challenge 2021. https:\/\/www.robots.ox.ac.uk\/~vgg\/data\/voxceleb\/competition2021.html"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.2462851"},{"key":"e_1_3_2_1_12_1","volume-title":"Equality of opportunity in supervised learning. Advances in Neural Information Processing Systems","author":"Hardt Moritz","year":"2016","unstructured":"Moritz Hardt, Eric Price, and Nathan Srebro. 2016. Equality of opportunity in supervised learning. Advances in Neural Information Processing Systems (2016), 3323\u20133331."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Khaled Hechmi Trung\u00a0Ngo Trong Ville Hautamaki and Tomi Kinnunen. 2021. VoxCeleb Enrichment for Age and Gender Recognition. (2021). http:\/\/arxiv.org\/abs\/2109.13510","DOI":"10.1109\/ASRU51503.2021.9688085"},{"key":"e_1_3_2_1_14_1","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 5115\u20135119","author":"Heigold Georg","year":"2016","unstructured":"Georg Heigold, Ignacio Moreno, Samy Bengio, and Noam Shazeer. 2016. End-to-End Text-Dependent Speaker Verification. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 5115\u20135119."},{"key":"e_1_3_2_1_15_1","volume-title":"Clova baseline system for the VoxCeleb speaker recognition challenge","author":"Heo Hee\u00a0Soo","year":"2020","unstructured":"Hee\u00a0Soo Heo, Bong\u00a0Jin Lee, Jaesung Huh, and Joon\u00a0Son Chung. 2020. Clova baseline system for the VoxCeleb speaker recognition challenge 2020. arXiv (2020), 1\u20133."},{"key":"e_1_3_2_1_16_1","unstructured":"Sara Hooker Nyalleng Moorosi Gregory Clark Samy Bengio and Emily Denton. 2020. Characterising Bias in Compressed Models. https:\/\/arxiv.org\/abs\/2010.03058"},{"key":"e_1_3_2_1_17_1","volume-title":"Surya Mattu and Lauren Kirchner","author":"Angwin Julia","year":"2016","unstructured":"Julia Angwin, Jeff Larson, Surya Mattu and Lauren Kirchner. 2016. Machine Bias. https:\/\/www.propublica.org\/article\/machine-bias-risk-assessments-in-criminal-sentencing"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2013.10.001"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICB.2013.6613025"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/1577069.1755843"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.009"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1915768117"},{"key":"e_1_3_2_1_23_1","volume-title":"Deep speaker: An end-to-end neural speaker embedding system. arXiv","author":"Li Chao","year":"2017","unstructured":"Chao Li, Xiaokong Ma, Bing Jiang, Xiangang Li, Xuewei Zhang, Xiao Liu, Ying Cao, Ajay Kannan, and Zhenyao Zhu. 2017. Deep speaker: An end-to-end neural speaker embedding system. arXiv (2017)."},{"key":"e_1_3_2_1_24_1","unstructured":"Beryl Lipton and Quintin Cooper. 2021. The Catalog of Carceral Surveillance: Voice Recognition and Surveillance. https:\/\/www.eff.org\/deeplinks\/2021\/09\/catalog-carceral-surveillance-voice-recognition-and-surveillance"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2248"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2015.00126"},{"key":"e_1_3_2_1_28_1","unstructured":"M McLaren L Ferrer D Castan and A Lawson. 2016. The Speakers in the Wild (SITW) speaker recognition database.. In Interspeech. pdfs.semanticscholar.org. https:\/\/pdfs.semanticscholar.org\/3fe3\/58a66359ee2660ec0d13e727eb8f3f0007c2.pdf"},{"key":"e_1_3_2_1_29_1","volume-title":"A survey on bias and fairness in machine learning. arXiv","author":"Mehrabi Ninareh","year":"2019","unstructured":"Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, and Aram Galstyan. 2019. A survey on bias and fairness in machine learning. arXiv (2019)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3375627.3375832"},{"key":"e_1_3_2_1_31_1","unstructured":"Marta Morr\u00e1s. 2021. BBVA Mexico allows its pensioner customers to provide proof of life from home thanks to Veridas voice biometrics. https:\/\/veridas.com\/en\/bbva-mexico-allows-pensioner-customers-provide-proof-of-life-from-home\/"},{"key":"e_1_3_2_1_32_1","unstructured":"Arsha Nagrani Joon\u00a0Son Chung Jaesung Huh Andrew Brown Ernesto Coto Weidi Xie Mitchell McLaren Douglas\u00a0A Reynolds and Andrew Zisserman. 2020. VoxSRC 2020: The Second VoxCeleb Speaker Recognition Challenge. (2020). http:\/\/arxiv.org\/abs\/2012.06867"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"e_1_3_2_1_34_1","volume-title":"Voxceleb: A large-scale speaker identification dataset. arXiv","author":"Nagrani Arsha","year":"2017","unstructured":"Arsha Nagrani, Joon\u00a0Son Chung, and Andrew Zisserman. 2017. Voxceleb: A large-scale speaker identification dataset. arXiv (2017), 2616\u20132620."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.06.001"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1815"},{"key":"e_1_3_2_1_37_1","volume-title":"NIST 2019 Speaker Recognition Evaluation Plan. 1","author":"NIST.","year":"2019","unstructured":"NIST. 2019. NIST 2019 Speaker Recognition Evaluation Plan. 1 (2019), 1\u20137."},{"key":"e_1_3_2_1_38_1","volume-title":"NIST 2020 CTS Speaker Recognition Challenge Evaluation Plan. Technical Report. 1\u20138 pages.","author":"NIST.","year":"2020","unstructured":"NIST. 2020. NIST 2020 CTS Speaker Recognition Challenge Evaluation Plan. Technical Report. 1\u20138 pages."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-523"},{"key":"e_1_3_2_1_40_1","volume-title":"Deep Face Recognition. In British Machine Vision Conference.","author":"Parkhi M","year":"2015","unstructured":"Omkar\u00a0M Parkhi, Andrea Vedaldi, and Andrew Zisserman. 2015. Deep Face Recognition. In British Machine Vision Conference."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1249"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314244"},{"key":"e_1_3_2_1_43_1","volume-title":"About Face: A Survey of Facial Recognition Evaluation.","author":"Raji Inioluwa\u00a0Deborah","year":"2021","unstructured":"Inioluwa\u00a0Deborah Raji and Genevieve Fried. 2021. About Face: A Survey of Facial Recognition Evaluation. (2021). http:\/\/arxiv.org\/abs\/2102.00813"},{"key":"e_1_3_2_1_44_1","volume-title":"An Overview of Automatic Speaker Recognition Technology","author":"Reynolds A.","year":"2002","unstructured":"Douglas\u00a0A. Reynolds. 2002. An Overview of Automatic Speaker Recognition Technology. IEEE (2002)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359246"},{"key":"e_1_3_2_1_46_1","volume-title":"where is my privacy? Exploring Accidental Triggers of Smart Speakers. (8","author":"Sch\u00f6nherr Lea","year":"2020","unstructured":"Lea Sch\u00f6nherr, Maximilian Golla, Thorsten Eisenhofer, Jan Wiele, Dorothea Kolossa, and Thorsten Holz. 2020. Unacceptable, where is my privacy? Exploring Accidental Triggers of Smart Speakers. (8 2020). http:\/\/arxiv.org\/abs\/2008.00508"},{"key":"e_1_3_2_1_47_1","volume-title":"3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings(2015)","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings(2015), 1\u201314."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","unstructured":"Rita Singh. 2019. Profiling Humans from their Voice. https:\/\/doi.org\/10.1007\/978-981-13-8403-5","DOI":"10.1007\/978-981-13-8403-5"},{"key":"e_1_3_2_1_49_1","volume-title":"Deep Neural Network Embeddings for Text-Independent Speaker Verification.Interspeech","author":"Snyder D","year":"2017","unstructured":"D Snyder, D Garcia-Romero, D Povey, and S Khudanpur. 2017. Deep Neural Network Embeddings for Text-Independent Speaker Verification.Interspeech (2017). https:\/\/www.isca-speech.org\/archive\/Interspeech_2017\/pdfs\/0620.PDF"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"crossref","unstructured":"Harini Suresh and John Guttag. 2021. A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle. In EAAMO \u201921: Equity and Access in Algorithms Mechanisms and Optimization.","DOI":"10.21428\/2c646de5.c16a07bb"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1746"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485730.3493448"},{"key":"e_1_3_2_1_54_1","unstructured":"Wiebke Toussaint Akhil Mathur Fahim Kawsar and Aaron\u00a0Yi Ding. 2022. Tiny always-on and fragile: Bias propagation through design choices in on-device machine learning workflows. (2022) 19\u00a0pages. http:\/\/arxiv.org\/abs\/2201.07677"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"crossref","unstructured":"Sandra Wachter Brent Mittelstadt and Chris Russell. 2021. Bias Preservation in Machine Learning : The Legality of Fairness Metrics Under EU Non- Discrimination Law. West Virginia Law Review Forthcoming(2021) 1\u201351. https:\/\/ssrn.com\/abstract=3792772","DOI":"10.2139\/ssrn.3792772"},{"key":"e_1_3_2_1_56_1","volume-title":"List of languages by number of native speakers in India. https:\/\/en.wikipedia.org\/wiki\/List_of_languages_by_number_of_native_speakers_in_India [Online","author":"Wikipedia","year":"2022","unstructured":"Wikipedia contributors. 2022. List of languages by number of native speakers in India. https:\/\/en.wikipedia.org\/wiki\/List_of_languages_by_number_of_native_speakers_in_India [Online; accessed 6-May-2022]."},{"key":"e_1_3_2_1_57_1","volume-title":"SUPERB: Speech processing Universal PERformance Benchmark.","author":"Chi Po-Han","year":"2021","unstructured":"Shu-wen Yang, Po-Han Chi, Yung-Sung Chuang, Cheng-I\u00a0Jeff Lai, Kushal Lakhotia, Yist\u00a0Y. Lin, Andy\u00a0T. Liu, Jiatong Shi, Xuankai Chang, Guan-Ting Lin, Tzu-Hsien Huang, Wei-Cheng Tseng, Ko-tik Lee, Da-Rong Liu, Zili Huang, Shuyan Dong, Shang-Wen Li, Shinji Watanabe, Abdelrahman Mohamed, and Hung-yi Lee. 2021. SUPERB: Speech processing Universal PERformance Benchmark. (2021). http:\/\/arxiv.org\/abs\/2105.01051"}],"event":{"name":"FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency","location":"Seoul Republic of Korea","acronym":"FAccT '22","sponsor":["ACM Association for Computing Machinery"]},"container-title":["2022 ACM Conference on Fairness Accountability and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3531146.3533089","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3531146.3533089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:10Z","timestamp":1750186930000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3531146.3533089"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,20]]},"references-count":56,"alternative-id":["10.1145\/3531146.3533089","10.1145\/3531146"],"URL":"https:\/\/doi.org\/10.1145\/3531146.3533089","relation":{},"subject":[],"published":{"date-parts":[[2022,6,20]]},"assertion":[{"value":"2022-06-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}