{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T07:56:14Z","timestamp":1779177374746,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Danmarks Frie Forskningsfond"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1145\/3656156.3663708","type":"proceedings-article","created":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T04:23:27Z","timestamp":1719807807000},"page":"249-252","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Cultures of the AI paralinguistic in voice cloning tools"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5503-5299","authenticated-orcid":false,"given":"Ada Ada","family":"Ada","sequence":"first","affiliation":[{"name":"IT University of Copenhagen, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6275-8966","authenticated-orcid":false,"given":"Stina Hasse","family":"J\u00f8rgensen","sequence":"additional","affiliation":[{"name":"Digital Design, IT University of Copenhagen, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9065-2843","authenticated-orcid":false,"given":"Jonas","family":"Fritsch","sequence":"additional","affiliation":[{"name":"Digital Design, IT University of Copenhagen, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Alexa Privacy: How Does Alexa Work?https:\/\/www.youtube.com\/watch?v=esMOQgDMAeo","year":"2020","unstructured":"Amazon. 2020. Alexa Privacy: How Does Alexa Work?https:\/\/www.youtube.com\/watch?v=esMOQgDMAeo"},{"key":"e_1_3_2_1_2_1","unstructured":"Apple. 2023. Siri. https:\/\/www.apple.com\/siri\/"},{"key":"e_1_3_2_1_3_1","first-page":"62","article-title":"Building synthetic voices","volume":"4","author":"Black W","year":"2003","unstructured":"Alan\u00a0W Black and Kevin\u00a0A Lenzo. 2003. Building synthetic voices. Language Technologies Institute, Carnegie Mellon University and Cepstral LLC 4, 2 (2003), 62.","journal-title":"Language Technologies Institute, Carnegie Mellon University and Cepstral LLC"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the ACM on human-computer interaction 3, CSCW","author":"Cambre Julia","year":"2019","unstructured":"Julia Cambre and Chinmay Kulkarni. 2019. One voice fits all? Social implications and research challenges of designing voices for smart devices. Proceedings of the ACM on human-computer interaction 3, CSCW (2019), 1\u201319."},{"key":"e_1_3_2_1_5_1","unstructured":"Coqui. 2023. Coqui. https:\/\/coqui.ai\/"},{"key":"e_1_3_2_1_6_1","unstructured":"ElevenLabs. 2024. ElevenLabs - Generative AI Text to Speech & Voice Cloning. https:\/\/elevenlabs.io\/"},{"key":"e_1_3_2_1_7_1","unstructured":"ElevenLabs. 2024. Prompting - ElevenLabs. https:\/\/elevenlabs.io\/docs\/speech-synthesis\/prompting"},{"key":"e_1_3_2_1_8_1","unstructured":"FakeYou. 2023. Creating a voice with FakeYou. https:\/\/docs.google.com\/document\/d\/1U4KVrY817-X_pPP-VLJuQFNw3_qGBU6HvWUp-PX5JeU\/edit?usp=embed_facebook"},{"key":"e_1_3_2_1_9_1","unstructured":"FakeYou. 2024. FakeYou Your Deep Fake Text to Speech Website.https:\/\/fakeyou.com"},{"key":"e_1_3_2_1_10_1","unstructured":"Google. 2024. Text-to-Speech AI: Lifelike Speech Synthesis. https:\/\/cloud.google.com\/text-to-speech\/"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","unstructured":"Jaehyeon Kim Jungil Kong and Juhee Son. 2021. Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech. https:\/\/doi.org\/10.48550\/arXiv.2106.06103","DOI":"10.48550\/arXiv.2106.06103"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Brandon LaBelle. 2014. Lexicon of the mouth: Poetics and politics of voice and the oral imaginary. A&C Black.","DOI":"10.5040\/9781501382802"},{"key":"e_1_3_2_1_13_1","unstructured":"Microsoft. 2023. Train your custom voice model - Speech service - Azure AI services. https:\/\/learn.microsoft.com\/en-us\/azure\/ai-services\/speech-service\/how-to-custom-voice-create-voice"},{"key":"e_1_3_2_1_14_1","volume-title":"The Guardian (Aug","author":"Parkinson Hannah\u00a0Jane","year":"2015","unstructured":"Hannah\u00a0Jane Parkinson. 2015. Hey, Siri! Meet the real people behind Apple\u2019s voice-activated assistant. The Guardian (Aug. 2015). https:\/\/www.theguardian.com\/technology\/2015\/aug\/12\/siri-real-voices-apple-ios-assistant-jon-briggs-susan-bennett-karen-jacobsen"},{"key":"e_1_3_2_1_15_1","unstructured":"RVC-Project. 2023. Retrieval-based-Voice-Conversion-WebUI. https:\/\/github.com\/RVC-Project\/Retrieval-based-Voice-Conversion-WebUI\/blob\/main\/docs\/en\/README.en.md"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28954-6"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Jonathan Shen Ruoming Pang Ron\u00a0J. Weiss Mike Schuster Navdeep Jaitly Zongheng Yang Zhifeng Chen Yu Zhang Yuxuan Wang R.\u00a0J. Skerry-Ryan Rif\u00a0A. Saurous Yannis Agiomyrgiannakis and Yonghui Wu. 2018. Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions. http:\/\/arxiv.org\/abs\/1712.05884","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"e_1_3_2_1_18_1","unstructured":"Suno AI. 2023. Bark. https:\/\/github.com\/suno-ai\/bark"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300833"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","unstructured":"Xu Tan Jiawei Chen Haohe Liu Jian Cong Chen Zhang Yanqing Liu Xi Wang Yichong Leng Yuanhao Yi Lei He Frank Soong Tao Qin Sheng Zhao and Tie-Yan Liu. 2022. NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality. https:\/\/doi.org\/10.48550\/arXiv.2205.04421","DOI":"10.48550\/arXiv.2205.04421"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","unstructured":"Haobin Tang Xulong Zhang Jianzong Wang Ning Cheng and Jing Xiao. 2023. EmoMix: Emotion Mixing via Diffusion Models for Emotional Speech Synthesis. https:\/\/doi.org\/10.48550\/arXiv.2306.00648","DOI":"10.48550\/arXiv.2306.00648"},{"key":"e_1_3_2_1_22_1","unstructured":"Uberduck. 2023. Uberduck | Make Music with AI Vocals. https:\/\/www.uberduck.ai\/"},{"key":"e_1_3_2_1_23_1","volume-title":"Tacotron: Towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135","author":"Wang Yuxuan","year":"2017","unstructured":"Yuxuan Wang, RJ Skerry-Ryan, Daisy Stanton, Yonghui Wu, Ron\u00a0J Weiss, Navdeep Jaitly, Zongheng Yang, Ying Xiao, Zhifeng Chen, Samy Bengio, and others. 2017. Tacotron: Towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135 (2017)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-122"}],"event":{"name":"DIS '24: Designing Interactive Systems Conference","location":"IT University of Copenhagen Denmark","acronym":"DIS '24","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Designing Interactive Systems Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3656156.3663708","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3656156.3663708","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:09:32Z","timestamp":1750295372000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3656156.3663708"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":24,"alternative-id":["10.1145\/3656156.3663708","10.1145\/3656156"],"URL":"https:\/\/doi.org\/10.1145\/3656156.3663708","relation":{},"subject":[],"published":{"date-parts":[[2024,7]]},"assertion":[{"value":"2024-07-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}