{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T05:54:48Z","timestamp":1782280488774,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,23]]},"DOI":"10.1145\/3715275.3732082","type":"proceedings-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T17:03:13Z","timestamp":1750698193000},"page":"1238-1249","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Labor, Power, and Belonging: The Work of Voice in the Age of AI Reproduction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7660-313X","authenticated-orcid":false,"given":"Shm","family":"Almeda","sequence":"first","affiliation":[{"name":"University of California, Berkeley, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4857-9498","authenticated-orcid":false,"given":"Robin","family":"Netzorg","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8807-9563","authenticated-orcid":false,"given":"Isabel","family":"Li","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7571-5387","authenticated-orcid":false,"given":"Ethan","family":"Tam","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6848-882X","authenticated-orcid":false,"given":"Skyla","family":"Ma","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7801-280X","authenticated-orcid":false,"given":"Bob Tianqi","family":"Wei","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,23]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"2024. AB 1836: Use of likeness: digital replica. | Digital Democracy \u2014 calmatters.digitaldemocracy.org. https:\/\/calmatters.digitaldemocracy.org\/bills\/ca_202320240ab1836."},{"key":"e_1_3_3_2_3_2","unstructured":"2024. AB 2602: Contracts against public policy: personal or professional services: digital replicas. | Digital Democracy \u2014 calmatters.digitaldemocracy.org. https:\/\/calmatters.digitaldemocracy.org\/bills\/ca_202320240ab2602."},{"key":"e_1_3_3_2_4_2","unstructured":"William Agnew Julia Barnett Annie Chu Rachel Hong Michael Feffer Robin Netzorg Harry\u00a0H. Jiang Ezra Awumey and Sauvik Das. 2024. Sound Check: Auditing Audio Datasets. arxiv:https:\/\/arXiv.org\/abs\/2410.13114\u00a0[cs.SD] https:\/\/arxiv.org\/abs\/2410.13114"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Alex Ahmed. 2020. We Will Not Be Pacified Through Participation. Tech Otherwise (oct 15 2020). https:\/\/techotherwise.pubpub.org\/pub\/qanxilt9.","DOI":"10.21428\/93b2c832.e4aa9a47"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642714"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445740"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713734"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604686"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS58808.2023.10374911"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","unstructured":"Susanne B\u00f8dker and Morten Kyng. 2018. Participatory Design that Matters\u2014Facing the Big Issues. ACM Trans. Comput.-Hum. Interact. 25 1 Article 4 (Feb. 2018) 31\u00a0pages. https:\/\/doi.org\/10.1145\/3152421","DOI":"10.1145\/3152421"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Virginia Braun and Victoria Clarke. 2006. Using thematic analysis in psychology. Qualitative research in psychology 3 2 (2006) 77\u2013101.","DOI":"10.1191\/1478088706qp063oa"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1037\/13620-004"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Simon Caton and Christian Haas. 2024. Fairness in Machine Learning: A Survey. ACM Comput. Surv. 56 7 Article 166 (April 2024) 38\u00a0pages. https:\/\/doi.org\/10.1145\/3616865","DOI":"10.1145\/3616865"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643834.3661545"},{"key":"e_1_3_3_2_16_2","unstructured":"Cheol\u00a0Jun Cho Peter Wu Tejas\u00a0S Prabhune Dhruv Agarwal and Gopala\u00a0K Anumanchipalli. 2024. Coding Speech through Vocal Tract Kinematics. IEEE Journal of Selected Topics in Signal Processing (2024)."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3532106.3533505"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3516392"},{"key":"e_1_3_3_2_19_2","unstructured":"Di Cooke Abigail Edwards Sophia Barkoff and Kathryn Kelly. 2024. As good as a coin toss human detection of ai-generated images videos audio and audiovisual stimuli. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.16760 (2024)."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Sefik\u00a0Emre Eskimez Xiaofei Wang Manthan Thakker Canrun Li Chung-Hsien Tsai Zhen Xiao Hemin Yang Zirun Zhu Min Tang Xu Tan et\u00a0al. 2024. E2 tts: Embarrassingly easy fully non-autoregressive zero-shot tts. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.18009 (2024).","DOI":"10.1109\/SLT61566.2024.10832320"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","unstructured":"Sarah\u00a0E. Fox Samantha Shorey Esther\u00a0Y. Kang Dominique Montiel\u00a0Valle and Estefania Rodriguez. 2023. Patchwork: The Hidden Human Labor of AI Integration within Essential Work. Proc. ACM Hum.-Comput. Interact. 7 CSCW1 Article 81 (April 2023) 20\u00a0pages. https:\/\/doi.org\/10.1145\/3579514","DOI":"10.1145\/3579514"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Jian Gao and Dashun Wang. 2024. Quantifying the use and potential benefits of artificial intelligence in scientific research. Nature human behaviour (2024) 1\u201312.","DOI":"10.1038\/s41562-024-02020-5"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658898"},{"key":"e_1_3_3_2_24_2","volume-title":"Ghost Work: How to Stop Silicon Valley from Building a New Global Underclass","author":"Gray Mary\u00a0L.","year":"2019","unstructured":"Mary\u00a0L. Gray and Siddharth Suri. 2019. Ghost Work: How to Stop Silicon Valley from Building a New Global Underclass. HarperCollins. Google-Books-ID: FFJkDwAAQBAJ."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658911"},{"key":"e_1_3_3_2_26_2","unstructured":"Lilly Irani. 2015. Justice for \u201cData Janitors\u201d. https:\/\/www.publicbooks.org\/justice-for-data-janitors\/"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604681"},{"key":"e_1_3_3_2_28_2","unstructured":"Zeqian Ju Yuancheng Wang Kai Shen Xu Tan Detai Xin Dongchao Yang Yanqing Liu Yichong Leng Kaitao Song Siliang Tang et\u00a0al. 2024. Naturalspeech 3: Zero-shot speech synthesis with factorized codec and diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.03100 (2024)."},{"key":"e_1_3_3_2_29_2","unstructured":"Haechan Kim Junho Myung Seoyoung Kim Sungpah Lee Dongyeop Kang and Juho Kim. 2024. LearnerVoice: A Dataset of Non-Native English Learners\u2019 Spontaneous Speech. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.04280 (2024)."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Dennis\u00a0H Klatt. 1987. Review of text-to-speech conversion for English. The Journal of the Acoustical Society of America 82 3 (1987) 737\u2013793.","DOI":"10.1121\/1.395275"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/633292.633461"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594070"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606831"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","unstructured":"Xuechen Liu Xin Wang Md Sahidullah Jose Patino H\u00e9ctor Delgado Tomi Kinnunen Massimiliano Todisco Junichi Yamagishi Nicholas Evans Andreas Nautsch and Kong\u00a0Aik Lee. 2023. ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild. IEEE\/ACM Transactions on Audio Speech and Language Processing 31 (2023) 2507\u20132522. https:\/\/doi.org\/10.1109\/TASLP.2023.3285283","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"e_1_3_3_2_36_2","unstructured":"Yisi Liu Bohan Yu Drake Lin Peter Wu Cheol\u00a0Jun Cho and Gopala\u00a0Krishna Anumanchipalli. 2024. Fast High-Quality and Parameter-Efficient Articulatory Synthesis using Differentiable DSP. arxiv:https:\/\/arXiv.org\/abs\/2409.02451\u00a0[eess.AS] https:\/\/arxiv.org\/abs\/2409.02451"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Kimberly\u00a0T Mai Sergi Bray Toby Davies and Lewis\u00a0D Griffin. 2023. Warning: Humans cannot reliably detect speech deepfakes. Plos one 18 8 (2023) e0285333.","DOI":"10.1371\/journal.pone.0285333"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","unstructured":"Luz Martinez-Lucas Wei-Cheng Lin and Carlos Busso. 2024. Analyzing Continuous-Time and Sentence-Level Annotations for Speech Emotion Recognition. IEEE Transactions on Affective Computing 15 3 (2024) 1754\u20131768. https:\/\/doi.org\/10.1109\/TAFFC.2024.3372380","DOI":"10.1109\/TAFFC.2024.3372380"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.67"},{"key":"e_1_3_3_2_40_2","unstructured":"NAVA. [n. d.]. AI QUESTIONS - NAVA \u2014 navavoices.org. https:\/\/navavoices.org\/ai-questions\/."},{"key":"e_1_3_3_2_41_2","unstructured":"NAVA. 2023. fAIr Voices: Consent Control Compensation \u2014 navavoices.org. https:\/\/navavoices.org\/fair-voices\/."},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594134"},{"key":"e_1_3_3_2_43_2","unstructured":"Vipula Rawte Amit Sheth and Amitava Das. 2023. A survey of hallucination in large foundation models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.05922 (2023)."},{"key":"e_1_3_3_2_44_2","unstructured":"SAG-AFTRA. 2023. 2023 TV\/Theatrical Contracts | SAG-AFTRA \u2014 sagaftra.org. https:\/\/www.sagaftra.org\/contracts-industry-resources\/contracts\/2023-tvtheatrical-contracts."},{"key":"e_1_3_3_2_45_2","unstructured":"SAG-AFTRA. 2023. ACTRA Needs Our Support \u2014 sagaftra.org. https:\/\/www.sagaftra.org\/actra-needs-our-support."},{"key":"e_1_3_3_2_46_2","unstructured":"SAG-AFTRA. 2024. Interactive Media (Video Game) Strike | SAG-AFTRA \u2014 sagaftra.org. https:\/\/www.sagaftra.org\/contracts-industry-resources\/contracts\/interactive-media-video-game-strike. [Accessed 22-01-2025]."},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"crossref","unstructured":"Eugenia San\u00a0Segundo Paul Foulkes Peter French Philip Harrison Vincent Hughes and Colleen Kavanagh. 2019. The use of the Vocal Profile Analysis for speaker characterization: Methodological proposals. Journal of the International Phonetic Association 49 3 (2019) 353\u2013380.","DOI":"10.1017\/S0025100318000130"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","unstructured":"Morgan\u00a0Klaus Scheuerman Alex Hanna and Emily Denton. 2021. Do Datasets Have Politics? Disciplinary Values in Computer Vision Dataset Development. Proc. ACM Hum.-Comput. Interact. 5 CSCW2 Article 317 (Oct. 2021) 37\u00a0pages. https:\/\/doi.org\/10.1145\/3476058","DOI":"10.1145\/3476058"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376338"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445107"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533132"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658992"},{"key":"e_1_3_3_2_53_2","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Udandarao Vishaal","year":"2024","unstructured":"Vishaal Udandarao, Ameya Prabhu, Adhiraj Ghosh, Yash Sharma, Philip Torr, Adel Bibi, Samuel Albanie, and Matthias Bethge. 2024. No\" zero-shot\" without exponential data: Pretraining concept frequency determines multimodal model performance. In The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_3_2_54_2","unstructured":"Apoorv Vyas Bowen Shi Matthew Le Andros Tjandra Yi-Chiao Wu Baishan Guo Jiemin Zhang Xinyue Zhang Robert Adkins William Ngan et\u00a0al. 2023. Audiobox: Unified audio generation with natural language prompts. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.15821 (2023)."},{"key":"e_1_3_3_2_55_2","unstructured":"Yuancheng Wang Haoyue Zhan Liwei Liu Ruihong Zeng Haotian Guo Jiachen Zheng Qiang Zhang Xueyao Zhang Shunsi Zhang and Zhizheng Wu. 2024. Maskgct: Zero-shot text-to-speech with masked generative codec transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.00750 (2024)."},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"crossref","unstructured":"Dongchao Yang Songxiang Liu Rongjie Huang Chao Weng and Helen Meng. 2024. Instructtts: Modelling expressive tts in discrete latent space with natural language style prompt. IEEE\/ACM Transactions on Audio Speech and Language Processing (2024).","DOI":"10.1109\/TASLP.2024.3402088"},{"key":"e_1_3_3_2_57_2","unstructured":"Xueyao Zhang Liumeng Xue Yicheng Gu Yuancheng Wang Jiaqi Li Haorui He Chaoren Wang Songting Liu Xi Chen Junan Zhang et\u00a0al. 2023. Amphion: An open-source audio music and speech generation toolkit. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.09911 (2023)."},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"crossref","unstructured":"Xuanru Zhou Anshul Kashyap Steve Li Ayati Sharma Brittany Morin David Baquirin Jet Vonk Zoe Ezzes Zachary Miller Maria Luisa\u00a0Gorno Tempini et\u00a0al. 2024. Yolo-stutter: End-to-end region-wise speech dysfluency detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.15297 (2024).","DOI":"10.21437\/Interspeech.2024-1855"}],"event":{"name":"FAccT '25: The 2025 ACM Conference on Fairness, Accountability, and Transparency","location":"Athens Greece","acronym":"FAccT '25"},"container-title":["Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3715275.3732082","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T11:23:35Z","timestamp":1750764215000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3715275.3732082"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,23]]},"references-count":57,"alternative-id":["10.1145\/3715275.3732082","10.1145\/3715275"],"URL":"https:\/\/doi.org\/10.1145\/3715275.3732082","relation":{},"subject":[],"published":{"date-parts":[[2025,6,23]]},"assertion":[{"value":"2025-06-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}