<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>2874</id>
    <completedYear/>
    <publishedYear>2024</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>10394</pageFirst>
    <pageLast>10427</pageLast>
    <pageNumber>34</pageNumber>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>Association for Computing Machinery (ACM)</publisherName>
    <publisherPlace>New York, NY, USA</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2024-05-11</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Giving Robots a Voice: Human-in-the-Loop Voice Creation and Open-Ended Labeling</title>
    <parentTitle language="eng">CHI '24: Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems</parentTitle>
    <identifier type="isbn">979-8-4007-0330-0</identifier>
    <identifier type="doi">10.1145/3613904.3642038</identifier>
    <enrichment key="opus_doi_flag">true</enrichment>
    <enrichment key="opus_import_data">{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T12:46:07Z","timestamp":1763037967153,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":90,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Leibniz award of Elisabeth Andr\u00e9","award":["AN 559\/10-1"]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,11]]},"DOI":"10.1145\/3613904.3642038","type":"proceedings-article","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:38:25Z","timestamp":1715416705000},"page":"1-34","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Giving Robots a Voice: Human-in-the-Loop Voice Creation and open-ended Labeling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4044-9123","authenticated-orcid":false,"given":"Pol","family":"van Rijn","sequence":"first","affiliation":[{"name":"Max Planck Institute for Empirical Aesthetics, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5230-5218","authenticated-orcid":false,"given":"Silvan","family":"Mertes","sequence":"additional","affiliation":[{"name":"Human-Centered Artificial Intelligence, Augsburg University, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5985-4973","authenticated-orcid":false,"given":"Kathrin","family":"Janowski","sequence":"additional","affiliation":[{"name":"Human-Centered Artificial Intelligence, Augsburg University, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1001-2278","authenticated-orcid":false,"given":"Katharina","family":"Weitz","sequence":"additional","affiliation":[{"name":"Human-Centered Artificial Intelligence, Augsburg University, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2868-0100","authenticated-orcid":false,"given":"Nori","family":"Jacoby","sequence":"additional","affiliation":[{"name":"Computational Auditory Perception Group, Max Planck Institute for Empirical Aesthetics, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2367-162X","authenticated-orcid":false,"given":"Elisabeth","family":"Andr\u00e9","sequence":"additional","affiliation":[{"name":"Human-Centered Artificial Intelligence, Augsburg University, Germany"}]}],"member":"320","published-online":{"date-parts":[[2024,5,11]]},"reference":[{"key":"e_1_3_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-35888-4_15"},{"key":"e_1_3_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9020267"},{"key":"e_1_3_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1101\/2022.05.10.491366"},{"key":"e_1_3_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3342775.3342806"},{"key":"e_1_3_3_3_6_1","volume-title":"Acoustic Profiles in Vocal Emotion Expression.Journal of Personality and Social Psychology 70, 3","author":"Banse Rainer","year":"1996","unstructured":"Rainer Banse and Klaus\u00a0R. Scherer. 1996. Acoustic Profiles in Vocal Emotion Expression.Journal of Personality and Social Psychology 70, 3 (1996), 614\u2013636. https:\/\/doi.org\/10\/fnrx63"},{"key":"e_1_3_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2020.05.007"},{"key":"e_1_3_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-008-0001-3"},{"key":"e_1_3_3_3_9_1","volume-title":"Gephi: An Open Source Software for Exploring and Manipulating Networks","author":"Bastian Mathieu","year":"2009","unstructured":"Mathieu Bastian, Sebastien Heymann, and Mathieu Jacomy. 2009. Gephi: An Open Source Software for Exploring and Manipulating Networks. http:\/\/www.aaai.org\/ocs\/index.php\/ICWSM\/09\/paper\/view\/154"},{"key":"e_1_3_3_3_10_1","unstructured":"Paul Boersma and David Weenink. 2018. Praat: doing phonetics by computer [Computer program]. Version 6.0.37 http:\/\/www.praat.org\/."},{"volume-title":"Designing Sociable Robots","author":"Breazeal Cynthia","key":"e_1_3_3_3_11_1","unstructured":"Cynthia Breazeal. 2004. Designing Sociable Robots. MIT Press."},{"key":"e_1_3_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3359325"},{"key":"e_1_3_3_3_13_1","unstructured":"Seamless Communication Lo\u00efc Barrault Yu-An Chung Mariano\u00a0Cora Meglioli David Dale Ning Dong Paul-Ambroise Duquenne Hady Elsahar Hongyu Gong Kevin Heffernan John Hoffman Christopher Klaiber Pengwei Li Daniel Licht Jean Maillard Alice Rakotoarison Kaushik\u00a0Ram Sadagopan Guillaume Wenzek Ethan Ye Bapi Akula Peng-Jen Chen Naji\u00a0El Hachem Brian Ellis Gabriel\u00a0Mejia Gonzalez Justin Haaheim Prangthip Hansanti Russ Howes Bernie Huang Min-Jae Hwang Hirofumi Inaguma Somya Jain Elahe Kalbassi Amanda Kallet Ilia Kulikov Janice Lam Daniel Li Xutai Ma Ruslan Mavlyutov Benjamin Peloquin Mohamed Ramadan Abinesh Ramakrishnan Anna Sun Kevin Tran Tuan Tran Igor Tufanov Vish Vogeti Carleigh Wood Yilin Yang Bokai Yu Pierre Andrews Can Balioglu Marta\u00a0R. Costa-juss\u00e0 Onur Celebi Maha Elbayad Cynthia Gao Francisco Guzm\u00e1n Justine Kao Ann Lee Alexandre Mourachko Juan Pino Sravya Popuri Christophe Ropers Safiyyah Saleem Holger Schwenk Paden Tomasello Changhan Wang Jeff Wang and Skyler Wang. 2023. SeamlessM4T: Massively Multilingual &amp; Multimodal Machine Translation. arxiv:2308.11596\u00a0[cs.CL]"},{"key":"e_1_3_3_3_14_1","doi-asserted-by":"publisher","DOI":"10.1177\/0305735600281002"},{"key":"e_1_3_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.1002\/per.1953"},{"key":"e_1_3_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1177\/1948550611430272"},{"key":"e_1_3_3_3_17_1","doi-asserted-by":"crossref","unstructured":"Anna Esposito Terry Amorese Marialucia Cuciniello Maria\u00a0Teresa Riviello Antonietta\u00a0Maria Esposito Alda Troncone and Gennaro Cordasco. 2019. The Dependability of Voice on Elders\u2019 Acceptance of Humanoid Agents.. In Interspeech. 31\u201335.","DOI":"10.21437\/Interspeech.2019-1734"},{"key":"e_1_3_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"e_1_3_3_3_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1349822.1349842"},{"key":"e_1_3_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2003.1251796"},{"key":"e_1_3_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0092-6566(03)00046-1"},{"key":"e_1_3_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.74.6.1464"},{"key":"e_1_3_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2559636.2559673"},{"key":"e_1_3_3_3_24_1","first-page":"10659","article-title":"Gibbs sampling with people","volume":"33","author":"Harrison Peter","year":"2020","unstructured":"Peter Harrison, Raja Marjieh, Federico Adolfi, Pol van Rijn, Manuel Anglada-Tort, Ofer Tchernichovski, Pauline Larrouy-Maestri, and Nori Jacoby. 2020. Gibbs sampling with people. Advances in Neural Information Processing Systems 33 (2020), 10659\u201310671.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.1207\/s15327051hci1904_2"},{"key":"e_1_3_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-322-80058-9_19"},{"key":"e_1_3_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/466029a"},{"key":"e_1_3_3_3_28_1","volume-title":"Integration of the big five and circumplex approaches to trait structure.Journal of personality and social psychology 63, 1","author":"Hofstee K","year":"1992","unstructured":"Willem\u00a0K Hofstee, Boele De\u00a0Raad, and Lewis\u00a0R Goldberg. 1992. Integration of the big five and circumplex approaches to trait structure.Journal of personality and social psychology 63, 1 (1992), 146."},{"key":"e_1_3_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2016.12.031"},{"key":"e_1_3_3_3_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.wocn.2018.07.001"},{"key":"e_1_3_3_3_31_1","volume-title":"International Journal of Social Robotics","author":"James Jesin","year":"2020","unstructured":"Jesin James, BT Balamurali, Catherine\u00a0I Watson, and Bruce MacDonald. 2020. Empathetic speech synthesis and testing for healthcare robots. International Journal of Social Robotics (2020), 1\u201319."},{"key":"e_1_3_3_3_32_1","doi-asserted-by":"publisher","unstructured":"Kathrin Janowski Hannes Ritschel and Elisabeth Andr\u00e9. 2022. Adaptive Artificial Personalities. In The Handbook on Socially Interactive Agents. ACM 155\u2013194. https:\/\/doi.org\/10.1145\/3563659.3563666","DOI":"10.1145\/3563659.3563666"},{"key":"e_1_3_3_3_33_1","volume-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis. Advances in neural information processing systems 31","author":"Jia Ye","year":"2018","unstructured":"Ye Jia, Yu Zhang, Ron Weiss, Quan Wang, Jonathan Shen, Fei Ren, Patrick Nguyen, Ruoming Pang, Ignacio Lopez\u00a0Moreno, Yonghui Wu, 2018. Transfer learning from speaker verification to multispeaker text-to-speech synthesis. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_3_3_34_1","first-page":"8067","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"Kim Jaehyeon","year":"2020","unstructured":"Jaehyeon Kim, Sungwon Kim, Jungil Kong, and Sungroh Yoon. 2020. Glow-tts: A generative flow for text-to-speech via monotonic alignment search. Advances in Neural Information Processing Systems 33 (2020), 8067\u20138077.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_3_35_1","volume-title":"International Conference on Machine Learning. PMLR, 5530\u20135540","author":"Kim Jaehyeon","year":"2021","unstructured":"Jaehyeon Kim, Jungil Kong, and Juhee Son. 2021. Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech. In International Conference on Machine Learning. PMLR, 5530\u20135540."},{"key":"e_1_3_3_3_36_1","unstructured":"Jaehyeon Kim Jungil Kong and Juhee Son. 2022. VITS implementation. https:\/\/github.com\/jaywalnut310\/vits."},{"key":"e_1_3_3_3_37_1","doi-asserted-by":"publisher","DOI":"10.1159\/000328433"},{"key":"e_1_3_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023345"},{"key":"e_1_3_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-014-0244-0"},{"key":"e_1_3_3_3_40_1","volume-title":"The human takes it all: Humanlike synthesized voices are perceived as less eerie and more likable. evidence from a subjective ratings study. Frontiers in neurorobotics","author":"K\u00fchne Katharina","year":"2020","unstructured":"Katharina K\u00fchne, Martin\u00a0H Fischer, and Yuefang Zhou. 2020. The human takes it all: Humanlike synthesized voices are perceived as less eerie and more likable. evidence from a subjective ratings study. Frontiers in neurorobotics (2020), 105."},{"key":"e_1_3_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1037\/a0036260"},{"key":"e_1_3_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"e_1_3_3_3_43_1","volume-title":"Proceedings of the 41th Annual Meeting of the Cognitive Science Society, CogSci 2019: Creativity + Cognition + Computation","author":"Langlois Thomas","year":"2019","unstructured":"Thomas Langlois, Nori Jacoby, Jordan\u00a0W. Suchow, and Tom Griffiths. 2019. Orthogonal multi-view three-dimensional object representations in memory revealed by serial reproduction. In Proceedings of the 41th Annual Meeting of the Cognitive Science Society, CogSci 2019: Creativity + Cognition + Computation, Montreal, Canada, July 24-27, 2019, Ashok\u00a0K. Goel, Colleen\u00a0M. Seifert, and Christian Freksa (Eds.). cognitivesciencesociety.org, 2078\u20132083. https:\/\/mindmodeling.org\/cogsci2019\/papers\/0363\/index.html"},{"key":"e_1_3_3_3_44_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2012938118"},{"key":"e_1_3_3_3_45_1","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog2802_4"},{"key":"e_1_3_3_3_46_1","volume-title":"Words are all you need? Capturing human sensory similarity with textual descriptors. arXiv preprint arXiv:2206.04105","author":"Marjieh Raja","year":"2022","unstructured":"Raja Marjieh, Pol van Rijn, Ilia Sucholutsky, Theodore\u00a0R. Sumers, Harin Lee, Thomas\u00a0L. Griffiths, and Nori Jacoby. 2022. Words are all you need? Capturing human sensory similarity with textual descriptors. arXiv preprint arXiv:2206.04105 (2022)."},{"key":"e_1_3_3_3_47_1","doi-asserted-by":"publisher","unstructured":"Maya\u00a0B. Mathur and David\u00a0B. Reichling. [n. d.]. Navigating a social world with robot partners: A quantitative cartography of the Uncanny Valley. 146 ([n. d.]) 22\u201332. https:\/\/doi.org\/10.1016\/j.cognition.2015.09.008","DOI":"10.1016\/j.cognition.2015.09.008"},{"key":"e_1_3_3_3_48_1","volume-title":"An introduction to the five-factor model and its applications.Journal of personality 60, 2","author":"McCrae RR","year":"1992","unstructured":"RR McCrae and OP John. 1992. An introduction to the five-factor model and its applications.Journal of personality 60, 2 (1992), 175."},{"key":"e_1_3_3_3_49_1","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"e_1_3_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2019.8673305"},{"key":"e_1_3_3_3_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11973-1_26"},{"key":"e_1_3_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACIIW52867.2021.9666349"},{"key":"e_1_3_3_3_53_1","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-020-01514-0"},{"key":"e_1_3_3_3_54_1","doi-asserted-by":"publisher","DOI":"10.1068\/i0415"},{"key":"e_1_3_3_3_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/mra.2012.2192811"},{"key":"e_1_3_3_3_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10246-w"},{"key":"e_1_3_3_3_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2006.314397"},{"key":"e_1_3_3_3_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/191666.191703"},{"key":"e_1_3_3_3_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/hri53351.2022.9889366"},{"key":"e_1_3_3_3_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3171221.3171268"},{"key":"e_1_3_3_3_62_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1716090115"},{"key":"e_1_3_3_3_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/1121241.1121280"},{"key":"e_1_3_3_3_64_1","volume-title":"International conference on machine learning. PMLR, 8748\u20138763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748\u20138763."},{"key":"e_1_3_3_3_65_1","unstructured":"Nicolas Ramirez-Guevara. 2017. Robotization Effect Using Phase Vocoder Processing. (2017)."},{"key":"e_1_3_3_3_66_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jrp.2006.02.001"},{"key":"e_1_3_3_3_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925487"},{"key":"e_1_3_3_3_68_1","volume-title":"Proceedings of the Australasian International Conference on Speech Science and Technology. Citeseer, 130\u2013135","author":"Roehling Sigrid","year":"2006","unstructured":"Sigrid Roehling, Bruce MacDonald, and Catherine Watson. 2006. Towards expressive speech synthesis in english on a robotic platform. In Proceedings of the Australasian International Conference on Speech Science and Technology. Citeseer, 130\u2013135."},{"key":"e_1_3_3_3_69_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogpsych.2009.07.001"},{"key":"e_1_3_3_3_70_1","doi-asserted-by":"publisher","DOI":"10.1002\/ejsp.2420080405"},{"key":"e_1_3_3_3_71_1","volume-title":"AWIS Magazine","author":"Schiebinger Londa","year":"2019","unstructured":"Londa Schiebinger. 2019. The robots are coming! But should they be gendered. AWIS Magazine, Winter (2019), 18\u201321, 58."},{"key":"e_1_3_3_3_72_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1587"},{"key":"e_1_3_3_3_73_1","doi-asserted-by":"publisher","DOI":"10.4135\/9781849200479.n24"},{"key":"e_1_3_3_3_74_1","doi-asserted-by":"publisher","unstructured":"Valentin Schwind. 2018. Implications of the uncanny valley of avatars and virtual characters for human-computer interaction. https:\/\/doi.org\/10.18419\/OPUS-9936","DOI":"10.18419\/OPUS-9936"},{"key":"e_1_3_3_3_75_1","doi-asserted-by":"publisher","unstructured":"Hubert Siuzdak Piotr Dura Pol van Rijn and Nori Jacoby. 2022. WavThruVec: Latent speech representation as intermediate features for neural speech synthesis. https:\/\/doi.org\/10.48550\/ARXIV.2203.16930","DOI":"10.48550\/ARXIV.2203.16930"},{"key":"e_1_3_3_3_76_1","volume-title":"arXiv preprint arXiv:2111.05095","author":"Stanton Daisy","year":"2021","unstructured":"Daisy Stanton, Matt Shannon, Soroosh Mariooryad, RJ Skerry-Ryan, Eric Battenberg, Tom Bagby, and David Kao. 2021. Speaker Generation. arXiv preprint arXiv:2111.05095 (2021)."},{"key":"e_1_3_3_3_77_1","doi-asserted-by":"publisher","unstructured":"Xu Tan Tao Qin Frank Soong and Tie-Yan Liu. 2021. A Survey on Neural Speech Synthesis. https:\/\/doi.org\/10.48550\/ARXIV.2106.15561","DOI":"10.48550\/ARXIV.2106.15561"},{"key":"e_1_3_3_3_78_1","doi-asserted-by":"publisher","DOI":"10.1504\/ijmrs.2015.068991"},{"key":"e_1_3_3_3_79_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2019.106215"},{"key":"e_1_3_3_3_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183654.3183691"},{"key":"e_1_3_3_3_81_1","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.59.4.781"},{"key":"e_1_3_3_3_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054556"},{"key":"e_1_3_3_3_83_1","volume-title":"Flowtron: An Autoregressive Flow-Based Generative Network for Text-to-Speech Synthesis. arXiv:2005.05957 [cs, eess]","author":"Valle Rafael","year":"2020","unstructured":"Rafael Valle, Kevin Shih, Ryan Prenger, and Bryan Catanzaro. 2020. Flowtron: An Autoregressive Flow-Based Generative Network for Text-to-Speech Synthesis. arXiv:2005.05957 [cs, eess] (2020). arxiv:2005.05957\u00a0[cs, eess]"},{"key":"e_1_3_3_3_84_1","unstructured":"Pol van Rijn Harin Lee and Nori Jacoby. 2022. Bridging the prosody GAP: Genetic Algorithm with People to efficiently sample emotional prosody In CogSci. arXiv preprint arXiv:2205.04820."},{"key":"e_1_3_3_3_85_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10855"},{"key":"e_1_3_3_3_86_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1538"},{"key":"e_1_3_3_3_87_1","unstructured":"Pol van Rijn Yue Sun Harin Lee Raja Marjieh Ilia Sucholutsky Francesca Lanzarini Elisabeth Andr\u00e9 and Nori Jacoby. 2023. Around the world in 60 words: A generative vocabulary test for online research. arXiv:arXiv:2302.01614"},{"key":"e_1_3_3_3_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376210"},{"key":"e_1_3_3_3_89_1","volume-title":"Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis. arXiv:1803.09017 [cs, eess]","author":"Wang Yuxuan","year":"2018","unstructured":"Yuxuan Wang, Daisy Stanton, Yu Zhang, R.\u00a0J. Skerry-Ryan, Eric Battenberg, Joel Shor, Ying Xiao, Fei Ren, Ye Jia, and Rif\u00a0A. Saurous. 2018. Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis. arXiv:1803.09017 [cs, eess] (2018). arxiv:1803.09017\u00a0[cs, eess]"},{"key":"e_1_3_3_3_90_1","doi-asserted-by":"publisher","DOI":"10.3758\/s13414-017-1361-2"},{"key":"e_1_3_3_3_91_1","doi-asserted-by":"publisher","DOI":"10.1098\/rspb.2012.3073"},{"key":"e_1_3_3_3_92_1","doi-asserted-by":"publisher","unstructured":"Junichi Yamagishi Christophe Veaux and Kirsten. MacDonald. 2019. CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit (version 0.92). https:\/\/doi.org\/10.7488\/DS\/2645","DOI":"10.7488\/DS"}],"event":{"name":"CHI '24: CHI Conference on Human Factors in Computing Systems","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGACCESS ACM Special Interest Group on Accessible Computing"],"location":"Honolulu HI USA","acronym":"CHI '24"},"container-title":["Proceedings of the CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642038","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613904.3642038","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:57:30Z","timestamp":1750291050000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642038"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,11]]},"references-count":90,"alternative-id":["10.1145\/3613904.3642038","10.1145\/3613904"],"URL":"https:\/\/doi.org\/10.1145\/3613904.3642038","relation":{},"subject":[],"published":{"date-parts":[[2024,5,11]]},"assertion":[{"value":"2024-05-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}</enrichment>
    <enrichment key="local_crossrefDocumentType">proceedings-article</enrichment>
    <enrichment key="local_crossrefLicence">https://creativecommons.org/licenses/by/4.0/</enrichment>
    <enrichment key="local_import_origin">crossref</enrichment>
    <enrichment key="local_doiImportPopulated">PersonAuthorFirstName_1,PersonAuthorLastName_1,PersonAuthorIdentifierOrcid_1,PersonAuthorFirstName_2,PersonAuthorLastName_2,PersonAuthorIdentifierOrcid_2,PersonAuthorFirstName_3,PersonAuthorLastName_3,PersonAuthorIdentifierOrcid_3,PersonAuthorFirstName_4,PersonAuthorLastName_4,PersonAuthorIdentifierOrcid_4,PersonAuthorFirstName_5,PersonAuthorLastName_5,PersonAuthorIdentifierOrcid_5,PersonAuthorFirstName_6,PersonAuthorLastName_6,PersonAuthorIdentifierOrcid_6,Enrichmentconference_title,Enrichmentconference_place,PublisherName,PublisherPlace,TitleMain_1,TitleParent_1,PageNumber,PageFirst,PageLast,CompletedYear,Enrichmentlocal_crossrefLicence</enrichment>
    <enrichment key="conference_title">CHI Conference on Human Factors in Computing Systems</enrichment>
    <enrichment key="conference_place">Honolulu HI USA</enrichment>
    <enrichment key="opus.source">doi-import</enrichment>
    <enrichment key="frontdoor_url">https://opus4.kobv.de/opus4-hs-augsburg/2874</enrichment>
    <enrichment key="OpenAccess">ja</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="HS_Augsburg_conferenceName">Conference on Human Factors in Computing Systems, CHI 2024, Honolulu, HI, USA, 11.05.2024 - 16.05.2024</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <licence>Creative Commons - CC-BY Namensnennung 4.0 International</licence>
    <author>Pol van Rijn</author>
    <author>Silvan Mertes</author>
    <author>Kathrin Janowski</author>
    <author>Katharina Weitz</author>
    <author>Nori Jacoby</author>
    <author>Elisabeth André</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>crowdsourcing</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>personalization</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>text/speech/language</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>robot</value>
    </subject>
    <collection role="ddc" number="004">Datenverarbeitung; Informatik</collection>
    <collection role="institutes" number="">Fakultät für Informatik</collection>
    <collection role="DFG-Fachsystematik" number="409">Informatik</collection>
    <collection role="persons" number="mertes">Mertes, Silvan (Prof. Dr.)</collection>
  </doc>
</export-example>
