{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T04:26:51Z","timestamp":1784003211111,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":103,"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-sa\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,11]]},"DOI":"10.1145\/3613904.3642040","type":"proceedings-article","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:38:06Z","timestamp":1715416686000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":37,"title":["Sound Designer-Generative AI Interactions: Towards Designing Creative Support Tools for Professional Sound Designers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0351-6574","authenticated-orcid":false,"given":"Purnima","family":"Kamath","sequence":"first","affiliation":[{"name":"Augmented Human Lab, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4512-4897","authenticated-orcid":false,"given":"Fabio","family":"Morreale","sequence":"additional","affiliation":[{"name":"School of Music, University of Auckland, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0359-2152","authenticated-orcid":false,"given":"Priambudi Lintang","family":"Bagaskara","sequence":"additional","affiliation":[{"name":"Augmented Human Lab, National University of Singapore (NUS), Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3124-6975","authenticated-orcid":false,"given":"Yize","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7441-5493","authenticated-orcid":false,"given":"Suranga","family":"Nanayakkara","sequence":"additional","affiliation":[{"name":"Augmented Human Lab, Department of Information Systems and Analytics, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,5,11]]},"reference":[{"key":"e_1_3_3_3_1_1","volume-title":"Musiclm: Generating music from text. arXiv preprint arXiv:2301.11325","author":"Agostinelli Andrea","year":"2023","unstructured":"Andrea Agostinelli, Timo\u00a0I Denk, Zal\u00e1n Borsos, Jesse Engel, Mauro Verzetti, Antoine Caillon, Qingqing Huang, Aren Jansen, Adam Roberts, Marco Tagliasacchi, 2023. Musiclm: Generating music from text. arXiv preprint arXiv:2301.11325 (2023)."},{"key":"e_1_3_3_3_2_1","volume-title":"https:\/\/openai.com\/dall-e-2 [Accessed","author":"Dall Open AI.","year":"2023","unstructured":"Open AI. 2023. Dall.E 2. https:\/\/openai.com\/dall-e-2 [Accessed: 29 August 2023]."},{"key":"e_1_3_3_3_3_1","volume-title":"https:\/\/openai.com\/blog\/chatgpt [Accessed","author":"Introducing Open AI.","year":"2023","unstructured":"Open AI. 2023. Introducing ChatGPT. https:\/\/openai.com\/blog\/chatgpt [Accessed: 29 August 2023]."},{"key":"e_1_3_3_3_4_1","volume-title":"https:\/\/www.aimi.fm\/ [Accessed","author":"Aimi Fm.","year":"2023","unstructured":"Aimi.Fm. 2023. Aimi.Fm. https:\/\/www.aimi.fm\/ [Accessed: 15 November 2023]."},{"key":"e_1_3_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300233"},{"key":"e_1_3_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"e_1_3_3_3_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3527927.3535200"},{"key":"e_1_3_3_3_8_1","volume-title":"brain.fm. https:\/\/www.brain.fm\/ [Accessed","year":"2023","unstructured":"brain.fm. 2023. brain.fm. https:\/\/www.brain.fm\/ [Accessed: 15 November 2023]."},{"key":"e_1_3_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1080\/2159676X.2019.1628806"},{"key":"e_1_3_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1080\/14780887.2020.1769238"},{"key":"e_1_3_3_3_11_1","doi-asserted-by":"publisher","DOI":"10.1080\/2159676X.2019.1704846"},{"key":"e_1_3_3_3_12_1","volume-title":"eXplainable AI approaches for debugging and diagnosis.XAI 4 Debugging Workshop at NEURIPS","author":"Bryan-Kinns Nick","year":"2021","unstructured":"Nick Bryan-Kinns, Berker Banar, Corey Ford, Courtney\u00a0N. Reed, Yixiao Zhang, Simon Colton, and Jack Armitage. 2021. Exploring XAI for the Arts: Explaining Latent Space in Generative Music, In eXplainable AI approaches for debugging and diagnosis.XAI 4 Debugging Workshop at NEURIPS 2021. https:\/\/openreview.net\/forum?id=GLhY_0xMLZr"},{"key":"e_1_3_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3591196.3593517"},{"key":"e_1_3_3_3_14_1","unstructured":"Alex Calderwood Vivian Qiu Katy\u00a0Ilonka Gero and Lydia\u00a0B Chilton. 2020. How Novelists Use Generative Language Models: An Exploratory User Study.. In HAI-GEN+ user2agent@ IUI."},{"key":"e_1_3_3_3_15_1","volume-title":"Practice based research: A guide. CCS report 1, 2","author":"Candy Linda","year":"2006","unstructured":"Linda Candy. 2006. Practice based research: A guide. CCS report 1, 2 (2006), 1\u201319."},{"key":"e_1_3_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1080\/15710880601007994"},{"key":"e_1_3_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3555578"},{"key":"e_1_3_3_3_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3134664"},{"key":"e_1_3_3_3_19_1","volume-title":"Audio-vision: sound on screen","author":"Chion Michel","unstructured":"Michel Chion. 2019. Audio-vision: sound on screen. Columbia University Press."},{"key":"e_1_3_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3563657.3596001"},{"key":"e_1_3_3_3_21_1","volume-title":"Foley sound synthesis at the dcase 2023 challenge. arXiv preprint arXiv:2304.12521","author":"Choi Keunwoo","year":"2023","unstructured":"Keunwoo Choi, Jaekwon Im, Laurie Heller, Brian McFee, Keisuke Imoto, Yuki Okamoto, Mathieu Lagrange, and Shinosuke Takamichi. 2023. Foley sound synthesis at the dcase 2023 challenge. arXiv preprint arXiv:2304.12521 (2023)."},{"key":"e_1_3_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3461778.3462050"},{"key":"e_1_3_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3172944.3172983"},{"key":"e_1_3_3_3_24_1","volume-title":"Simple and Controllable Music Generation. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=jtiQ26sCJi","author":"Copet Jade","year":"2023","unstructured":"Jade Copet, Felix Kreuk, Itai Gat, Tal Remez, David Kant, Gabriel Synnaeve, Yossi Adi, and Alexandre D\u00e9fossez. 2023. Simple and Controllable Music Generation. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=jtiQ26sCJi"},{"key":"e_1_3_3_3_25_1","volume-title":"The atlas of AI: Power, politics, and the planetary costs of artificial intelligence","author":"Crawford Kate","unstructured":"Kate Crawford. 2021. The atlas of AI: Power, politics, and the planetary costs of artificial intelligence. Yale University Press."},{"key":"e_1_3_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-017-9088-8_14"},{"key":"e_1_3_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2856767.2856795"},{"key":"e_1_3_3_3_28_1","volume-title":"Intelligent Music Production","author":"De\u00a0Man Brecht","unstructured":"Brecht De\u00a0Man, Ryan Stables, and Joshua\u00a0D Reiss. 2019. Intelligent Music Production. Routledge."},{"key":"e_1_3_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3027063.3027072"},{"key":"e_1_3_3_3_30_1","volume-title":"https:\/\/endel.io\/ [Accessed","year":"2023","unstructured":"Endel. 2023. Endel. https:\/\/endel.io\/ [Accessed: 15 November 2023]."},{"key":"e_1_3_3_3_31_1","volume-title":"https:\/\/huggingface.co\/ [Accessed","author":"Face Hugging","year":"2023","unstructured":"Hugging Face. 2023. Hugging Face. https:\/\/huggingface.co\/ [Accessed: 15 November 2023]."},{"key":"e_1_3_3_3_32_1","volume-title":"The machine learning algorithm as creative musical tool. arXiv preprint arXiv:1611.00379","author":"Fiebrink Rebecca","year":"2016","unstructured":"Rebecca Fiebrink and Baptiste Caramiaux. 2016. The machine learning algorithm as creative musical tool. arXiv preprint arXiv:1611.00379 (2016)."},{"key":"e_1_3_3_3_33_1","volume-title":"Proceedings of The Eleventh International Society for Music Information Retrieval Conference (ISMIR 2010)","author":"Fiebrink Rebecca","year":"2010","unstructured":"Rebecca Fiebrink and Perry\u00a0R Cook. 2010. The Wekinator: a system for real-time, interactive machine learning in music. In Proceedings of The Eleventh International Society for Music Information Retrieval Conference (ISMIR 2010)(Utrecht), Vol.\u00a03. Citeseer, 2\u20131."},{"key":"e_1_3_3_3_34_1","volume-title":"Speculating on Reflection and People\u2019s Music Co-Creation with AI. Workshop on Generative AI and HCI at the CHI Conference on Human Factors in Computing Systems 2022","author":"Ford Corey","year":"2022","unstructured":"Corey Ford and Nick Bryan-Kinns. 2022. Speculating on Reflection and People\u2019s Music Co-Creation with AI. Workshop on Generative AI and HCI at the CHI Conference on Human Factors in Computing Systems 2022 (2022)."},{"key":"e_1_3_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300619"},{"key":"e_1_3_3_3_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376514"},{"key":"e_1_3_3_3_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/642611.642653"},{"key":"e_1_3_3_3_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580999"},{"key":"e_1_3_3_3_39_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_40_1","volume-title":"Deep Learning","author":"Goodfellow J.","unstructured":"Ian\u00a0J. Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. MIT Press, Cambridge, MA, USA. http:\/\/www.deeplearningbook.org."},{"key":"e_1_3_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096328"},{"key":"e_1_3_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.5113511"},{"key":"e_1_3_3_3_43_1","doi-asserted-by":"crossref","unstructured":"Aaron Hertzmann. 2018. Can computers create art?. In Arts Vol.\u00a07. MDPI 18.","DOI":"10.3390\/arts7020018"},{"key":"e_1_3_3_3_44_1","volume-title":"Advances in Neural Information Processing Systems, H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, and H.\u00a0Lin (Eds.). Vol.\u00a033. Curran Associates","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. In Advances in Neural Information Processing Systems, H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, and H.\u00a0Lin (Eds.). Vol.\u00a033. Curran Associates, Inc., 6840\u20136851. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/4c5bcfec8584af0d967f1ab10179ca4b-Paper.pdf"},{"key":"e_1_3_3_3_45_1","volume-title":"Monica Dinculescu, and Carrie\u00a0J Cai.","author":"Huang Zhi\u00a0Anna","year":"2020","unstructured":"Cheng-Zhi\u00a0Anna Huang, Hendrik\u00a0Vincent Koops, Ed Newton-Rex, Monica Dinculescu, and Carrie\u00a0J Cai. 2020. AI song contest: Human-AI co-creation in songwriting. arXiv preprint arXiv:2010.05388 (2020)."},{"key":"e_1_3_3_3_46_1","volume-title":"https:\/\/pytorch.org\/hub\/ [Accessed","author":"Hub Pytorch","year":"2023","unstructured":"Pytorch Hub. 2023. Pytorch Hub. https:\/\/pytorch.org\/hub\/ [Accessed: 15 November 2023]."},{"key":"e_1_3_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2095667.2095671"},{"key":"e_1_3_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-72116-9_22"},{"key":"e_1_3_3_3_49_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.4813465"},{"key":"e_1_3_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445093"},{"key":"e_1_3_3_3_51_1","unstructured":"Purnima Kamath Chitralekha Gupta Lonce Wyse and Suranga Nanayakkara. 2023. Example-Based Framework for Perceptually Guided Audio Texture Generation. arxiv:2308.11859\u00a0[eess.AS]"},{"key":"e_1_3_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_3_3_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581641.3584078"},{"key":"e_1_3_3_3_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357236.3395494"},{"key":"e_1_3_3_3_55_1","volume-title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=a-xFK8Ymz5J","author":"Kong Zhifeng","year":"2021","unstructured":"Zhifeng Kong, Wei Ping, Jiaji Huang, Kexin Zhao, and Bryan Catanzaro. 2021. DiffWave: A Versatile Diffusion Model for Audio Synthesis. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=a-xFK8Ymz5J"},{"key":"e_1_3_3_3_56_1","volume-title":"Understanding the art of sound organization","author":"Landy Leigh","unstructured":"Leigh Landy. 2007. Understanding the art of sound organization. Mit Press."},{"key":"e_1_3_3_3_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3563657.3595977"},{"key":"e_1_3_3_3_58_1","unstructured":"Sara Lenzi. 2021. The design of data sonification. Design processes protocols and tools grounded in anomaly detection. (2021)."},{"key":"e_1_3_3_3_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/1142405.1142428"},{"key":"e_1_3_3_3_60_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0202)","author":"Liu Haohe","year":"2023","unstructured":"Haohe Liu, Zehua Chen, Yi Yuan, Xinhao Mei, Xubo Liu, Danilo Mandic, Wenwu Wang, and Mark\u00a0D Plumbley. 2023. AudioLDM: Text-to-Audio Generation with Latent Diffusion Models. In Proceedings of the 40th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0202), Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). PMLR, 21450\u201321474. https:\/\/proceedings.mlr.press\/v202\/liu23f.html"},{"key":"e_1_3_3_3_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376739"},{"key":"e_1_3_3_3_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3490099.3511159"},{"key":"e_1_3_3_3_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3519809"},{"key":"e_1_3_3_3_64_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2005.04.002"},{"key":"e_1_3_3_3_65_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a097)","author":"Marafioti Andr\u00e9s","year":"2019","unstructured":"Andr\u00e9s Marafioti, Nathana\u00ebl Perraudin, Nicki Holighaus, and Piotr Majdak. 2019. Adversarial Generation of Time-Frequency Features with application in audio synthesis. In Proceedings of the 36th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a097), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 4352\u20134362. https:\/\/proceedings.mlr.press\/v97\/marafioti19a.html"},{"key":"e_1_3_3_3_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/2967508"},{"key":"e_1_3_3_3_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517511"},{"key":"e_1_3_3_3_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544549.3573794"},{"key":"e_1_3_3_3_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3503719"},{"key":"e_1_3_3_3_70_1","volume-title":"Sound design theory and practice: Working with sound","author":"Murray Leo","unstructured":"Leo Murray. 2019. Sound design theory and practice: Working with sound. Routledge."},{"key":"e_1_3_3_3_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174223"},{"key":"e_1_3_3_3_72_1","unstructured":"Sangshin Oh Minsung Kang Hyeongi Moon Keunwoo Choi and Ben\u00a0Sangbae Chon. 2023. A Demand-Driven Perspective on Generative Audio AI. arxiv:2307.04292\u00a0[eess.AS]"},{"key":"e_1_3_3_3_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"e_1_3_3_3_74_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems, H.\u00a0Wallach, H.\u00a0Larochelle, A.\u00a0Beygelzimer, F.\u00a0d'Alch\u00e9-Buc, E.\u00a0Fox, and R.\u00a0Garnett (Eds.). Vol.\u00a032. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/bdbca288fee7f92f2bfa9f7012727740-Paper.pdf"},{"key":"e_1_3_3_3_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2678166"},{"key":"e_1_3_3_3_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3519026"},{"key":"e_1_3_3_3_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414472"},{"key":"e_1_3_3_3_78_1","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2021.0060"},{"key":"e_1_3_3_3_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00158"},{"key":"e_1_3_3_3_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/1323688.1323689"},{"key":"e_1_3_3_3_81_1","doi-asserted-by":"crossref","unstructured":"Ben Shneiderman. 2022. Human-centered AI. Oxford University Press.","DOI":"10.1093\/oso\/9780192845290.001.0001"},{"key":"e_1_3_3_3_82_1","volume-title":"Spectromorphology: explaining sound-shapes. Organised sound 2, 2","author":"Smalley Denis","year":"1997","unstructured":"Denis Smalley. 1997. Spectromorphology: explaining sound-shapes. Organised sound 2, 2 (1997), 107\u2013126."},{"key":"e_1_3_3_3_83_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"e_1_3_3_3_84_1","volume-title":"Denoising Diffusion Implicit Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=St1giarCHLP","author":"Song Jiaming","year":"2021","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2021. Denoising Diffusion Implicit Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=St1giarCHLP"},{"key":"e_1_3_3_3_85_1","volume-title":"Advances in Neural Information Processing Systems, M.\u00a0Ranzato, A.\u00a0Beygelzimer, Y.\u00a0Dauphin, P.S. Liang, and J.\u00a0Wortman Vaughan (Eds.). Vol.\u00a034. Curran Associates","author":"Song Yang","year":"2021","unstructured":"Yang Song, Conor Durkan, Iain Murray, and Stefano Ermon. 2021. Maximum Likelihood Training of Score-Based Diffusion Models. In Advances in Neural Information Processing Systems, M.\u00a0Ranzato, A.\u00a0Beygelzimer, Y.\u00a0Dauphin, P.S. Liang, and J.\u00a0Wortman Vaughan (Eds.). Vol.\u00a034. Curran Associates, Inc., 1415\u20131428. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/0a9fdbb17feb6ccb7ec405cfb85222c4-Paper.pdf"},{"key":"e_1_3_3_3_86_1","unstructured":"Angie Spoto Natalia Oleynik Sebastian Deterding and Jon Hook. 2017. Library of Mixed-Initiative Creative Interfaces."},{"key":"e_1_3_3_3_87_1","volume-title":"Audio Engineering Society Convention 150","author":"J.","unstructured":"Christian\u00a0J. Steinmetz and Joshua Reiss. 2021. pyloudnorm: A simple yet flexible loudness meter in Python. In Audio Engineering Society Convention 150. http:\/\/www.aes.org\/e-lib\/browse.cfm?elib=21076"},{"key":"e_1_3_3_3_88_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445219"},{"key":"e_1_3_3_3_89_1","doi-asserted-by":"publisher","DOI":"10.3366\/sound.2014.0057"},{"key":"e_1_3_3_3_90_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.4813402"},{"key":"e_1_3_3_3_91_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.3672956"},{"key":"e_1_3_3_3_92_1","volume-title":"WaveNet: A Generative Model for Raw Audio. CoRR abs\/1609.03499","author":"van\u00a0den Oord A\u00e4ron","year":"2016","unstructured":"A\u00e4ron van\u00a0den Oord, Sander Dieleman, Heiga Zen, Karen Simonyan, Oriol Vinyals, Alex Graves, Nal Kalchbrenner, Andrew\u00a0W. Senior, and Koray Kavukcuoglu. 2016. WaveNet: A Generative Model for Raw Audio. CoRR abs\/1609.03499 (2016). arXiv:1609.03499http:\/\/arxiv.org\/abs\/1609.03499"},{"key":"e_1_3_3_3_93_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174021"},{"key":"e_1_3_3_3_94_1","doi-asserted-by":"publisher","DOI":"10.23919\/DAFx51585.2021.9768298"},{"key":"e_1_3_3_3_95_1","unstructured":"Graham Wallas. 1926. The art of thought. Vol.\u00a010. Harcourt Brace."},{"key":"e_1_3_3_3_96_1","volume-title":"IUI Workshops. https:\/\/api.semanticscholar.org\/CorpusID:255825625","author":"Weisz D.","year":"2023","unstructured":"Justin\u00a0D. Weisz, Michael\u00a0J. Muller, Jessica He, and Stephanie Houde. 2023. Toward General Design Principles for Generative AI Applications 130-144. In IUI Workshops. https:\/\/api.semanticscholar.org\/CorpusID:255825625"},{"key":"e_1_3_3_3_97_1","volume-title":"What are diffusion models?lilianweng.github.io (Jul","author":"Weng Lilian","year":"2021","unstructured":"Lilian Weng. 2021. What are diffusion models?lilianweng.github.io (Jul 2021). https:\/\/lilianweng.github.io\/posts\/2021-07-11-diffusion-models\/"},{"key":"e_1_3_3_3_98_1","unstructured":"Anna Wiener. 2022. The Weird Analog Delights of Foley Sound Effects. https:\/\/www.newyorker.com\/magazine\/2022\/07\/04\/the-weird-analog-delights-of-foley-sound-effects"},{"key":"e_1_3_3_3_99_1","volume-title":"Real-valued parametric conditioning of an RNN for interactive sound synthesis. arXiv preprint arXiv:1805.10808","author":"Wyse Lonce","year":"2018","unstructured":"Lonce Wyse. 2018. Real-valued parametric conditioning of an RNN for interactive sound synthesis. arXiv preprint arXiv:1805.10808 (2018)."},{"key":"e_1_3_3_3_100_1","volume-title":"Artificial Intelligence in Music, Sound, Art and Design, Tiago Martins, Nereida Rodr\u00edguez-Fern\u00e1ndez, and S\u00e9rgio\u00a0M","author":"Wyse Lonce","unstructured":"Lonce Wyse, Purnima Kamath, and Chitralekha Gupta. 2022. Sound Model Factory: An Integrated System Architecture for\u00a0Generative Audio Modelling. In Artificial Intelligence in Music, Sound, Art and Design, Tiago Martins, Nereida Rodr\u00edguez-Fern\u00e1ndez, and S\u00e9rgio\u00a0M. Rebelo (Eds.). Springer International Publishing, Cham, 308\u2013322."},{"key":"e_1_3_3_3_101_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"e_1_3_3_3_102_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397481.3450663"},{"key":"e_1_3_3_3_103_1","volume-title":"https:\/\/modelzoo.co\/ [Accessed","author":"Zoo Model","year":"2023","unstructured":"Model Zoo. 2023. Model Zoo. https:\/\/modelzoo.co\/ [Accessed: 15 November 2023]."}],"event":{"name":"CHI '24: CHI Conference on Human Factors in Computing Systems","location":"Honolulu HI USA","acronym":"CHI '24","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGACCESS ACM Special Interest Group on Accessible Computing"]},"container-title":["Proceedings of the CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642040","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613904.3642040","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\/3613904.3642040"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,11]]},"references-count":103,"alternative-id":["10.1145\/3613904.3642040","10.1145\/3613904"],"URL":"https:\/\/doi.org\/10.1145\/3613904.3642040","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"}}]}}