{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T05:56:49Z","timestamp":1751608609740,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,2]],"date-time":"2024-05-02T00:00:00Z","timestamp":1714608000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2021R1A4A1032582"],"award-info":[{"award-number":["NRF-2021R1A4A1032582"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information & communications Technology Planning & Evaluation","award":["RS-2022-00155966"],"award-info":[{"award-number":["RS-2022-00155966"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,2]]},"DOI":"10.1145\/3613905.3650785","type":"proceedings-article","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:15:21Z","timestamp":1715415321000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Understanding the Use of AI-Based Audio Generation Models by End-Users"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1580-8940","authenticated-orcid":false,"given":"Jiyeon","family":"Han","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, Ewha Womans University, Korea, Republic of"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9654-2110","authenticated-orcid":false,"given":"Eunseo","family":"Yang","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Ewha Womans University, Korea, Republic of"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7832-6313","authenticated-orcid":false,"given":"Uran","family":"Oh","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Ewha Womans University, Korea, Republic of"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,11]]},"reference":[{"key":"e_1_3_3_3_1_1","volume-title":"Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information fusion 58","author":"Arrieta Alejandro\u00a0Barredo","year":"2020","unstructured":"Alejandro\u00a0Barredo Arrieta, Natalia D\u00edaz-Rodr\u00edguez, Javier Del\u00a0Ser, Adrien Bennetot, Siham Tabik, Alberto Barbado, Salvador Garc\u00eda, Sergio Gil-L\u00f3pez, Daniel Molina, Richard Benjamins, 2020. Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information fusion 58 (2020), 82\u2013115."},{"key":"e_1_3_3_3_2_1","volume-title":"Audiolm: a language modeling approach to audio generation","author":"Borsos Zal\u00e1n","year":"2023","unstructured":"Zal\u00e1n Borsos, Rapha\u00ebl Marinier, Damien Vincent, Eugene Kharitonov, Olivier Pietquin, Matt Sharifi, Dominik Roblek, Olivier Teboul, David Grangier, Marco Tagliasacchi, 2023. Audiolm: a language modeling approach to audio generation. IEEE\/ACM Transactions on Audio, Speech, and Language Processing (2023)."},{"doi-asserted-by":"crossref","unstructured":"Shaiful\u00a0Alam Chowdhury and Dwight\u00a0J Makaroff. 2013. Popularity Growth Patterns of YouTube Videos-A Category-based Study.. In WEBIST. Citeseer 233\u2013242.","key":"e_1_3_3_3_3_1","DOI":"10.5220\/0004372802330242"},{"volume-title":"The algorithmic composer. Vol.\u00a016. AR Editions","author":"Cope David","unstructured":"David Cope. 2000. The algorithmic composer. Vol.\u00a016. AR Editions, Inc.","key":"e_1_3_3_3_4_1"},{"key":"e_1_3_3_3_5_1","volume-title":"Simple and Controllable Music Generation. Advances in Neural Information Processing Systems 36","author":"Copet Jade","year":"2024","unstructured":"Jade Copet, Felix Kreuk, Itai Gat, Tal Remez, David Kant, Gabriel Synnaeve, Yossi Adi, and Alexandre D\u00e9fossez. 2024. Simple and Controllable Music Generation. Advances in Neural Information Processing Systems 36 (2024)."},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_6_1","DOI":"10.1145\/1965724.1965742"},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_7_1","DOI":"10.2307\/3397876"},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_8_1","DOI":"10.4135\/9781849208574"},{"key":"e_1_3_3_3_9_1","volume-title":"Generative adversarial nets. Advances in neural information processing systems 27","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_3_3_10_1","volume-title":"Music composition with deep learning: A review. Advances in speech and music technology: computational aspects and applications","author":"Hernandez-Olivan Carlos","year":"2022","unstructured":"Carlos Hernandez-Olivan and Jose\u00a0R Beltran. 2022. Music composition with deep learning: A review. Advances in speech and music technology: computational aspects and applications (2022), 25\u201350."},{"key":"e_1_3_3_3_11_1","volume-title":"Long short-term memory. Neural computation 9, 8","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735\u20131780."},{"key":"e_1_3_3_3_12_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma P","year":"2013","unstructured":"Diederik\u00a0P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_13_1","DOI":"10.1145\/3581641.3584078"},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_14_1","DOI":"10.1007\/978-3-031-35891-3_36"},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_15_1","DOI":"10.1145\/3394171.3414032"},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_16_1","DOI":"10.1109\/MMUL.2020.3046491"},{"key":"e_1_3_3_3_17_1","first-page":"1","article-title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu Pengfei","year":"2023","unstructured":"Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2023. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. Comput. Surveys 55, 9 (2023), 1\u201335.","journal-title":"Comput. Surveys"},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_18_1","DOI":"10.1145\/3491102.3501825"},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_19_1","DOI":"10.1109\/ICSC.2018.00077"},{"unstructured":"Kristine Monteith Virginia Francisco Tony\u00a0R Martinez Pablo Gerv\u00e1s and Dan Ventura. 2011. Automatic Generation of Emotionally-Targeted Soundtracks.. In ICCC. 60\u201362.","key":"e_1_3_3_3_20_1"},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_21_1","DOI":"10.1145\/3539618.3592000"},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_22_1","DOI":"10.1145\/2642918.2647406"},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_23_1","DOI":"10.58496\/MJCSC\/2023\/006"},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_24_1","DOI":"10.1145\/3571884.3597144"},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_25_1","DOI":"10.1109\/TVCG.2022.3209479"},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_26_1","DOI":"10.1109\/MMUL.2010.44"},{"key":"e_1_3_3_3_27_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_28_1","DOI":"10.1609\/aaai.v33i01.33011174"},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_29_1","DOI":"10.1109\/CAI54212.2023.00105"},{"volume-title":"Formalized music: thought and mathematics in composition. Number\u00a06","author":"Xenakis Iannis","unstructured":"Iannis Xenakis. 1992. Formalized music: thought and mathematics in composition. Number\u00a06. Pendragon Press.","key":"e_1_3_3_3_30_1"},{"key":"e_1_3_3_3_31_1","volume-title":"Diffsound: Discrete diffusion model for text-to-sound generation","author":"Yang Dongchao","year":"2023","unstructured":"Dongchao Yang, Jianwei Yu, Helin Wang, Wen Wang, Chao Weng, Yuexian Zou, and Dong Yu. 2023. Diffsound: Discrete diffusion model for text-to-sound generation. IEEE\/ACM Transactions on Audio, Speech, and Language Processing (2023)."},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_32_1","DOI":"10.1111\/mice.12954"},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_33_1","DOI":"10.1109\/ITNEC.2019.8729266"}],"event":{"sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGACCESS ACM Special Interest Group on Accessible Computing"],"acronym":"CHI '24","name":"CHI '24: CHI Conference on Human Factors in Computing Systems","location":"Honolulu HI USA"},"container-title":["Extended Abstracts of the CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613905.3650785","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613905.3650785","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:44:17Z","timestamp":1750290257000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613905.3650785"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,2]]},"references-count":33,"alternative-id":["10.1145\/3613905.3650785","10.1145\/3613905"],"URL":"https:\/\/doi.org\/10.1145\/3613905.3650785","relation":{},"subject":[],"published":{"date-parts":[[2024,5,2]]},"assertion":[{"value":"2024-05-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}