Novice-AI Music Co-Creation via AI-Steering Tools for Deep Generative Models
Open accessThe DOI matches its Crossref record; 36 of the 37 references it cites were found in a registry or an index.
Abstract
While generative deep neural networks (DNNs) have demonstrated their capacity for creating novel musical compositions, less attention has been paid to the challenges and potential of co-creating with these musical AIs, especially for novices. In a needfinding study with a widely used, interactive musical AI, we found that the AI can overwhelm users with the amount of musical content it generates, and frustrate them with its non-deterministic output. To better match co-creation needs, we developed AI-steering tools, consisting of Voice Lanes that restrict content generation to particular voices; Example-Based Sliders to control the similarity of generated content to an existing example; Semantic Sliders to nudge music generation in high-level directions (happy/sad, conventional/surprising); and Multiple Alternatives of generated content to audition and choose from. In a summative study (N=21), we discovered the tools not only increased users' trust, control, comprehension, and sense of collaboration with the AI, but also contributed to a greater sense of self-efficacy and ownership of the composition relative to the AI.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures




Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Creative industries employ vision-aligned proactive and semiproactive agency.”
From Exploring Collaboration Patterns and Strategies in Human-AI Co-creation through the Lens of Agency: A Scoping Review of the Top-tier HCI Literature (2025) · cites this paper as [109]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Mapping interaction flows reveals prevalent patterns and underexplored areas, such as the sparse use of 'Auditory Interaction' [84, 109, 164], signaling innovation opportunities in domains like assistive technology or music co-creation.”
From Exploring Collaboration Patterns and Strategies in Human-AI Co-creation through the Lens of Agency: A Scoping Review of the Top-tier HCI Literature (2025) · cites this paper as [109]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“AI agency patterns are typically co-operative or semi-active [66, 191], often involving a shared or dynamically negotiated locus of control [8, 47, 109].”
From Exploring Collaboration Patterns and Strategies in Human-AI Co-creation through the Lens of Agency: A Scoping Review of the Top-tier HCI Literature (2025) · cites this paper as [109]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The locus of control can be dynamic, shifting between human guidance and AI generation [8, 109], often operating at a fine granularity for detailed adjustments [208].”
From Exploring Collaboration Patterns and Strategies in Human-AI Co-creation through the Lens of Agency: A Scoping Review of the Top-tier HCI Literature (2025) · cites this paper as [109]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In contrast to software engineering, other domains including Human-Computer Interaction (HCI), organization and business management, and cognitive science have explored the impact of LLMs on creativity.”
From The Impact of Generative AI on Creativity in Software Development: A Research Agenda (2025) · cites this paper as [77]
Experimental — accuracy not yet measured
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Using thematic analysis in psychology
Braun, V., & Clarke, V. (2006) · Qualitative Research in Psychology · doi:10.1191/1478088706qp063oa · Cited by 194,414
Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing
Benjamini, Y., & Hochberg, Y. (1995) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1995.tb02031.x · Cited by 109,482 · cited 1×
“To analyze the quantitative measures, we conducted paired t-tests using Benjamani-Hochberg correction [3] to account for the 15 planned-comparisons (using a false discovery rate Q = 0 .”
MethodDevelopment of NASA-TLX (Task Load Index): Results of Empirical and Theoretical Research
(1988) · Advances in Psychology · doi:10.1016/s0166-4115(08)62386-9 · Cited by 15,003 · cited 2×
“Effort: Users answered the effort question of the NASA-TLX [25], where 1=very low and 7=very high.”
Method(2016) · Cited by 11,679
An integrative model of organizational trust
Mayer, R. C., Davis, J. H., & Schoorman, F. D. (1995) · The Academy of Management Review · doi:10.2307/258792 · Cited by 10,736 · cited 1×
“Trust : Participants rated the system along Mayer’s dimensions of trust [35]: capability, benevolence, and integrity.”
BackgroundGuidelines for Human-AI Interaction
Amershi, S., Weld, D., Vorvoreanu, M., Fourney, A., Nushi, B., Collisson, P., Suh, J., Iqbal, S., Bennett, P. N., Inkpen, K., et al. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300233 · Cited by 2,439 · cited 3×
“Previous research suggests benefits of educating users about the AI and its capabilities [1], or providing onboarding materials and exercises [6].”
BackgroundCai, C. J., Winter, S., Steiner, D., Wilcox, L., & Terry, M. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359206 · Cited by 594 · cited 1×
“Previous research suggests benefits of educating users about the AI and its capabilities [1], or providing onboarding materials and exercises [6].”
BackgroundSelf-citationEnabling Factorized Piano Music Modeling and Generation with the MAESTRO DatasetPreprint
Hawthorne, C., Stasyuk, A., Roberts, A., Simon, I., Huang, C.-Z. A., Dieleman, S., Elsen, E., Engel, J., & Eck, D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.12247 · Cited by 471 · cited 1×
“Research has demonstrated the potential for modeling and synthesizing music, ranging from singlevoice sequences [13] and multi-part music [19, 34], to music with variable parts at each time step [4] and music with longterm structure over minutes [30, 37, 26].”
BackgroundSelf-citationBoulanger-Lewandowski, N., Bengio, Y., & Vincent, P. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1206.6392 · Cited by 459 · cited 1×
“Research has demonstrated the potential for modeling and synthesizing music, ranging from singlevoice sequences [13] and multi-part music [19, 34], to music with variable parts at each time step [4] and music with longterm structure over minutes [30, 37, 26].”
BackgroundDeepBach: a Steerable Model for Bach Chorales GenerationPreprint
Hadjeres, G., Pachet, F., & Nielsen, F. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.01010 · Cited by 449 · cited 7×
“The conventional interface does include interactive control features via the infillmask feature (present in both conditions) which enables users to crop any region of music to be regenerated [11, 24].”
BackgroundMethodInfluential
Research works printed but not linked: 6
- 8. Kate Compton and Michael Mateas. 2015. Casual Creators. In Proceedings of the Sixth International Conference on Computational Creativity (ICCC 2015),
- 9. Hannu Toivonen, Simon Colton, Michael Cook, and Dan Ventura (Eds.). Brigham Young University, Park City, Utah, 228-235. http://computationalcreativity.net/ iccc2015/proceedings/10_2Compton.pdf
- 12. Monica Dinculescu and Cheng-Zhi Anna Huang. 2019. Coucou: An Expanded Interface for Interactive Composition with Coconet, through Flexible Inpainting. (2019). https://coconet.glitch.me/
- 33. Hannu Toivonen, Simon Colton, Michael Cook, and Dan Ventura (Eds.). Brigham Young University, Park City, Utah, 236-243. http://computationalcreativity.net/ iccc2015/proceedings/10_3Jacob.pdf
- 36. Feynman Liang. 2016. BachBot: Automatic Composition in the Style of Bach Chorales. Masters thesis, University of Cambridge (2016).
- 42. Ralf Schwarzer and Matthias Jerusalem. 1995. Generalized Self-efficacy Scale. Measures in Health Psychology: A User's Portfolio. Causal and Control Beliefs 1, 1 (1995), 35-37.
Cited by
Items 201–300 of 409
The role of generative AI in facilitating social interactions: A scoping review
Arets, T., Perugia, G., Houben, M., & IJsselsteijn, W. A. (2026) · Computers in Human Behavior Reports · doi:10.1016/j.chbr.2026.101300 · Cited by 10
“Cococo, developed by Louie et al. [44] in 2020, is a web-based music editor designed for human-AI co-creation, improving traditional generative music interfaces with AI-guided specialized tools for creative control.”
Designing Human-AI Collaboration to Support Learning in Counterspeech Writing
Ding, X., Ping, K., Gunturi, U. S., Carik, B., Stil, S., Wilhelm, L. A., Daryanto, T., E.Hawdon, J., Lee, S. W., & Rho, E. H. R. (2025) · IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) · doi:10.1109/vl-hcc65237.2025.00052 · Cited by 10
“Future work may further explore how interaction design supports perceptions of authorship and trust [54]–[56].”
InfluentialComparative Evaluation in the Wild: Systems for the Expressive Rendering of Music
Worrall, K., Yin, Z., & Collins, T. (2024) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2024.3408717 · Cited by 10
Ouyang, J., Wu, M., Li, X., Deng, H., Jin, Z., & Wu, D. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3446829 · Cited by 11
“…BCI and multi-brain to multi-robot interaction, which were barely tackled in previous works but good for metaverse scenariossuchasgenerativeAI[34],autonomousmanufacturing orunmannedfactory,andImmersivetechnologyorextended reality(XR),withmassiveaccessandcontrolunderanin-creasing number of…”
BackgroundAffinder: Expressing Concepts of Situations that Afford Activities using Context-Detectors
Louie, R., Gergle, D., & Zhang, H. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3501902 · Cited by 10
“Studies of human-AI music co-creation have observed cases where a human creator will change their own concepts of how to express a human emotion through music, based on interacting with music alternatives generated by the AI [30].”
BackgroundSelf-citationBlanchard, L., Naseck, P., Egozy, E., & Paradiso, J. A. (2024) · doi:10.21428/e4baedd9.69c11de7 · Cited by 10
MOSAAIC: Managing Optimization towards Shared Autonomy, Authority, and Initiative in Co-creationPreprint
Issak, A., Rezwana, J., & Harteveld, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.11481 · Cited by 11
Kariyawasam, H., Niwarthana, A., Palmer, A., Kay, J., & Withana, A. (2024) · Proceedings of the 29th International Conference on Intelligent User Interfaces · doi:10.1145/3640543.3645161 · Cited by 9
“Research shows that involving users in creative processes enhances emotional well-being, and user experience, and brings fun and excitement to the user [7, 28, 47], and increases the user’s sense of ownership of the generated content [22].”
BackgroundContext-AI Tunes: Context-Aware AI-Generated Music for Stress Reduction
Wei, X., Zhang, Z., Yue, Z., & Chen, H. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-93418-6_22 · Cited by 9
“In the field of music therapy, there is growing interest in human-AI collaboration for creative activities such as live performances [3,17], composition [13,29], and production [30].”
Sculpt-to-Image: Exploring Clay-based Sculpting to Support Human-AI-Co-Creation of Images
Hesselbarth, L., Wenig, N., Döring, T., & Malaka, R. (2025) · Creativity and Cognition · doi:10.1145/3698061.3734408 · Cited by 10
“Such as using AI for co-writing stories [57], letting children create visual narratives [19], or co-creation of music [33].”
Faruqi, F., Abdel-Rahman, A., Tejedor, L., Nisser, M., Li, J., Phadnis, V., Jampani, V., Gershenfeld, N., Hofmann, M. K., & Mueller, S. (2025) · ACM Symposium on Computational Fabrication (SCF) · doi:10.1145/3745778.3766655 · Cited by 9
“Co-creation tools based on Generative AI allow users to create new content by leveraging Deep Learning methods to learn from existing data in the form of text [Chowdhery et al. 2023], images [Rombach et al. 2022], music [Louie et al. 2020], and 3D models [Gao et al. 2022].”
Exploring gestural affordances in audio latent space navigation
Zheng, S. J., Xambó, A., & Bryan–Kinns, N. (2025) · Frontiers in Computer Science · doi:10.3389/fcomp.2025.1575202 · Cited by 9
Human-AI Co-Creation: A New Interaction Paradigm for Human-AI Interaction
Davis, N., Clemens, M., Rezwana, J., & Browne, E. (2025) · Springer eBooks · doi:10.1007/978-981-97-8440-0_76-1 · Cited by 9
An Exploration of Default Images in Text-to-Image Generation
Simonen, H., Kiviniemi, A., Johnston, H., Barranha, H., & Oppenlaender, J. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790681 · Cited by 9
“We describe these images and make nine postulates about their characteristics.”
“Control Is a Trajectory, Not a Point”: Conceptualizing Control in Human-AI Co-Creativity
Issak, A., Rezwana, J., & Harteveld, C. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790861 · Cited by 9
“Research posits control as the transition point between human and AI contribution [50], where, in a novice-AI music co-creation, the AI is designed to take on more control during routine tasks but cede control to the human during critical or complex situations [82].”
Enhancing collaborative signing songwriting experience of the d/Deaf individuals
Choi, Y., Lee, C., Chung, S., Cho, E., Yoo, S., & Hong, J.-H. (2024) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2024.103382 · Cited by 9
Lowy, R., Magiawala, K., Mittal, S., Hall, K., Roberts, J., & Kim, J. G. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3687050 · Cited by 9
“…to consider factors that will make this data both easy to understand for this group while building interactive tools to create a feeling of ownership of the products, for example by building accessible visualizations [99] and including opportunities to manipulate and direct AI output [57].”
Toward Co-Creative Tools for Tactical Urban Revitalization
Cooney, S. (2021) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3411763.3443426 · Cited by 9
“The HCI community has explored co-creative systems in a variety of contexts, such as sketching [26], journalism [21], music creation [19], and even recipe creation [27].”
BackgroundShijian, L., Zhitong, C., Juncheng, S., Ting, C., & Deyin, Z. (2023) · Journal of Mechanical Engineering · doi:10.3901/jme.2023.11.065 · Cited by 8
Follow My Logic: Generative AI Workflows in Designing for Serious Table-Top Games
Ma, L., Pan, M., Siu, V., Chang, X., Holopainen, J. P., Li, J., & Lc, R. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-92823-9_11 · Cited by 8
Interactive Storyboarding for Rapid Visual Story Generation
Jo, S., Yuan, Z., & Kim, S.-W. (2022) · IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia) · doi:10.1109/icce-asia57006.2022.9954679 · Cited by 8
BRIEDGE: EEG-Adaptive Edge AI for Multi-Brain to Multi-Robot InteractionPreprint
Ouyang, J., Wu, M., Li, X., Deng, H., & Wu, D. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2403.15432 · Cited by 8
“…BCI and multi-brain to multi-robot interaction, which were barely tackled in previous works but good for metaverse scenarios such as co-creation [41], autonomous manufacturing or unmanned factory [67], and Immersive technology or extended reality (XR) [40], with massive access and control under…”
BackgroundAdaptive Human-Agent Teaming: A Review of Empirical Studies from the Process Dynamics PerspectivePreprint
Wang, M., Wu, J., Ma, S., Li, N., Zhang, P., Gu, N., & Lu, T. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.10918 · Cited by 8
“Metrics like relationship , rapport , and sense of collaboration are used to measure members’ teaming experience[3, 94, 129, 138, 181], potentially showing future possibilities working together.”
InfluentialBurlin, C. (2023) · DiVA (Luleå University of Technology) · Cited by 8
PLay: Parametrically Conditioned Layout Generation using Latent Diffusion
Cheng, C.-Y., Huang, F., Li, G., & Li, Y. (2023) · arXiv · doi:10.48550/arxiv.2301.11529 · Cited by 7
“More importantly, for users to enjoy co-designing with generative models and trust the generated layouts, they need to be able to express their design ideas and drive the generation process (Louie et al., 2020).”
BackgroundFitria, T. N. (2025) · International Journal of Computer and Information System (IJCIS) · doi:10.29040/ijcis.v6i3.230 · Cited by 8
Yu, T., Xu, J., & Pan, Y. (2024) · Journal of Eye Movement Research · doi:10.16910/jemr.17.5.3 · Cited by 7
“The utilization of deep learning methodologies (Louie et al., 2020), particularly Generative Adversarial Networks (GANs), in artistic production has garnered significant interest and thorough investigation (Karras et al., 2020).”
The Use of AI in Advertising Creativity: Impact on the Receiver
Piñero, M. S., Palazón, M. M. C. P. C., & Acosta-López, M. J. (2025) · Advances in marketing, customer relationship management, and e-services book series · doi:10.4018/979-8-3693-3799-8.ch002 · Cited by 8
From Metrics to Meaning: Time to Rethink Evaluation in Human–AI Collaborative Design
Walton, S. P., Evans, B. J., Rahat, A., Stovold, J., & Vincalek, J. (2025) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3773292 · Cited by 7
“Over time the PCG community shifted emphasis onto how generative tools could be used to support the design process [9] leading to a wide range of mixed-initiative algorithms and techniques [5, 8, 13, 20, 32, 39].”
Breaking the Boundaries: Philosophical Encounters with Artificial Intelligence in Music Education
Jiang, R. (2025) · Action Criticism and Theory for Music Education · doi:10.22176/act24.3.53 · Cited by 7
Changing Your Tune: Lessons for Using Music to Encourage Physical Activity
Clark, M., & Doryab, A. (2024) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3659611 · Cited by 7
“In this approach, a song is generated using Bach CoCoCo [38], and musical features are adjusted to communicate wellness levels.”
MethodTransparency in Music-Generative AI: A Systematic Literature ReviewPreprint
Batlle-Roca, R., Gómez, E., Liao, W., Serra, X., & Mitsufuji, Y. (2024) · Research Square · doi:10.21203/rs.3.rs-3708077/v2 · Cited by 7
Tchemeube, R. B., Ens, J., Plut, C., Pasquier, P., Safi, M., Grabit, Y., & Rolland, J.-B. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.14071 · Cited by 8
“Finally, Louie et al. [ Louie et al. , 2020 ] compare Bach-doodle [ Huang et al. , 2019 ] ) with infill mask and the Cococo interface with interactive steering controls: voice lanes, semantic sliders, and generative alternatives.”
BackgroundResultCreative ML Assemblages: The Interactive Politics of People, Processes, and Products
Shelby, R., Srinivasan, R., Burgdorf, K., Lena, J. C., & Rostamzadeh, N. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3637315 · Cited by 6
“• Products : This element refers to the ML-mediated outcomes of creative processes, and may take many forms including visual art [61], fashion [141], music [108, 156, 157], and animation or motion design [127], among others.”
BackgroundWeaver, A. (2025) · AI & Society · doi:10.1007/s00146-025-02291-0 · Cited by 6
“Louie et al. (2020) posits that, for musical creatives to feel meaningfully involved in GenAI processes, there must be a limit to the amount of information generated at any one time.”
Design Probes for AI-Driven AAC: Addressing Complex Communication Needs in Aphasia
Mao, L., Lee, J. H., Faroqi‐Shah, Y., & Valencia, S. (2025) · Designing Interactive Systems Conference · doi:10.1145/3715336.3735736 · Cited by 7
“However, prior research has successfully involved PwA throughout the design process, empowering them and enhancing their autonomy [76].”
Hrnjić, A., Pilav-Velić, A., Hadžiahmetović, N., & Dedović, L. (2025) · South East European Journal of Economics and Business · doi:10.2478/jeb-2025-0020 · Cited by 6
Music Composition as a Lens for Understanding Human-AI Collaboration
Gianet, E. T., Di Caro, L., & Rapp, A. (2024) · Institutional Research Information System University of Turin (University of Turin) · Cited by 6
Human-AI Interfaces are a Central Component of Trustworthy AI
Plass, M., Kargl, M., Evans, T., Brčić, L., Regitnig, P., Geißler, C., Carvalho, R., Jansen, C., Zerbe, N., Holzinger, A., et al. (2022) · Intelligent systems reference library · doi:10.1007/978-3-031-12807-3_11 · Cited by 6
Yakura, H., & Goto, M. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2307.13005 · Cited by 6
“Louie et al. [49] proposed an interactive interface for novice users so that they can use a symbolic music generation technique with control of happiness or randomness.”
BackgroundLong, T., & Peng, W. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.14091 · Cited by 6
Composer's Assistant 2: Interactive Multi-Track MIDI Infilling with Fine-Grained User ControlPreprint
Malandro, M. E. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.14700 · Cited by 6
“Cococo [25] is a DAW-like interface to Co-conet, supporting 4 tracks and arbitrary user-driven infill-ing/part rewriting, similar to DeepBach.”
ResultHow Do Human Creators Embrace Human-AI Co-Creation? A Perspective on Human Agency of Screenwriters
Tang, Y., Zhou, J., Li, H., Xie, X., Ma, X., & Qu, H. (2026) · Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790300 · Cited by 5
“…decision-making:inmusiccomposition,“steering”toolshelped novicespartitioncomplextasksandstrengthenedtheirsenseof ownershipandcompetence[41,58];instoryauthoring,AItools enableddesignerstofocusonnarrativechoiceswhileretaining controlovertheoutput[29,52].”
GastroConcerto: Towards Designing Auditory Dining System to Enrich Chefs’ Culinary Practices
Wang, H., Deng, J., Kong, D., Fang, Z., Luo, H., Pasumarthy, N., Patibanda, R., Abewickrema, S., Fang, X. Z., Elvitigala, D. S., et al. (2025) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3706599.3719700 · Cited by 5
“HCI researchers are increasingly interested in developing systems to support creativity using AI [32], interactive technologies [1, 56], and information systems [34] to aid practitioners in fields like education [26, 27], painting [36], etc.”
Human-AI Interaction Patterns in Creative Domains and Their Time-Based Visualization
Leger, R., & Buschek, D. (2025) · Mensch und Computer (MuC) · doi:10.1145/3743049.3743081 · Cited by 5
Pedagogy of the Prompt: Music Education, Artificial Intelligence, and Big Tech Magic
bell, A. P. (2025) · Action Criticism and Theory for Music Education · doi:10.22176/act24.3.202 · Cited by 6
VidTune: Creating Video Soundtracks with Generative Music and Contextual Thumbnails
Huh, M., Fraser, C. A., Li, D., Dontcheva, M., & Wang, B. K. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791572 · Cited by 5
“Modern text-to-music models [22, 85, 91] also make end-to-end music generation more accessible to novices [62] and creators with hearing impairments [19] by allowing them to describe desired moods or styles in natural language.”
Fang, C., Guo, J., Khiatani, P. V., Lin, H., Zhang, B., Yenigün, E. Ö., & Wang, S. G. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2658255 · Cited by 6
Co-Performing Music with AI: Real-Time Performance Control Using Speech and Gestures
Borovik, I., & Viro, V. (2023) · Frontiers in artificial intelligence and applications · doi:10.3233/faia230097 · Cited by 5
Understanding User Experience with AI-Assisted Writing Service
Kim, G., Kim, J., & Kim, H. K. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-35894-4_19 · Cited by 5
Correia, A., Schneider, D., Fonseca, B., Mohseni, H., Kujala, T., & Kärkkäinen, T. (2024) · International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA) · doi:10.1109/hora61326.2024.10550680 · Cited by 5
“…music co-creation encompass a disparate spectrum of perspectives that range from envisioning AI as a “companion” [23] or a “collaborative improvising drummer” [24], to seeing it as a “music composer” [8-10], a “drawer” [26], or a “steering tool” that enhances musicians’ creative ownership [9].”
BackgroundMAICO: A Visualization Design Study on AI-Assisted Music Composition
Rau, S., Heyen, F., Brachtel, B., & Sedlmair, M. (2025) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2025.3539779 · Cited by 5
“Although interfaces that provide more control perform better, offer more authorship, and are therefore preferred by users [42], [43], research in this area is sparse compared to AI development [12].”
MoodSmith: Enabling Mood-Consistent Multimedia for AI-Generated Advocacy CampaignsPreprint
Menon, S., Wang, S., & Chilton, L. B. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2403.12356 · Cited by 5
“For audio, Co-coco [11] supports music generation according to emotional quality, such as minor vs major tones; An automated generation system [18] creates emotionally relevant music scores for the speech of audio stories, spanning four basic emotions: happy, sad, nervous, and calm.”
BackgroundBreaking the Midas Spell:Understanding Progressive Novice-AI Collaboration in Spatial DesignPreprint
Wan, Z., Tang, J., Cai, L., Tong, X., & Liu, C. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.20124 · Cited by 6
“Rapid advances in Generative AI technology have enabled AI to actively collaborate with humans in the creation of new content, particularly in writing, drawing, coding, music, and even 3D asset creation [9, 14, 21, 25, 28, 29].”
BackgroundDesign Probes for AI-Driven AAC: Addressing Complex Communication Needs in AphasiaPreprint
Mao, L., Lee, J. H., Shah, Y. F., & Valencia, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.09435 · Cited by 5
“However, prior research has successfully involved PwA throughout the design process, empowering them and enhancing their autonomy [76].”
ReaLJam: Real-Time Human-AI Music Jamming with Reinforcement Learning-Tuned TransformersPreprint
Scarlatos, A., Wu, Y., Simon, I., Roberts, A., Cooijmans, T., Jaques, N., Tarakajian, C., & Huang, C.-Z. A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.21267 · Cited by 5
“While there are many prior works on real-time human-AI collaboration in music [2–4, 7, 17–19, 23, 26, 27], only one studies a real-time jamming system [2], but does not fully address the above challenges (see a detailed related work in Appendix B).”
InfluentialSelf-citationExploring Real-Time Music-to-Image Systems for Creative Inspiration in Music Creation
Yang, M., Llano, M. T., & McCormack, J. (2024) · Monash University Research Portal (Monash University) · doi:10.48550/arxiv.2407.05584 · Cited by 4
“The systematic evaluation of GPT-2’s musical outputs, as discussed in Louie et al. (2020), underscores the model’s potential in this domain.”
BackgroundApplication of Artificial Intelligence-based Music Generation Technology in Popular Music Production
Wang, F. (2025) · Journal of Combinatorial Mathematics and Combinatorial Computing · doi:10.61091/jcmcc127a-038 · Cited by 4
Kim, H. S., Han, S., & Hong, J.-W. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2025.2570097 · Cited by 4
“…AI to write articles quickly, create images depicting once-imagined fantasies or virtual worlds, and upload videos that previously required high-end computer graphics editing, all primarily through online platforms such as YouTube, TikTok, and Instagram (Louie et al., 2020; Lyu et al., 2024).”
Human-Centered AI Design Principles for Generative AI
Weisz, J. D., He, J., & Muller, M. J. (2025) · Springer eBooks · doi:10.1007/978-981-95-3658-0_74 · Cited by 4
CoLyricist: Enhancing Lyric Writing with AI through Workflow-Aligned Support
Yoshida, M., Li, B. Q., Zhao, S., Zhou, Q., Hu, S., Chen, X. '., & Peng, N. (2026) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3742413.3789099 · Cited by 4
“Supporting melody editing directly or enabling smoother integration with external composition tools remains an important direction for future work, informed by prior research on melody composition support [20, 32, 40].”
Venus and Mars on Canvas: AI-Mediated Collaborative Drawing for Romantic Relationship Insight
Won, H., Kim, J., Kim, J., Kim, T., & Han, J. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791153 · Cited by 4
“In music composition and design contexts, AI can suggest motifs and variations that enrich the creative process [3, 9, 12, 13, 39, 55].”
Choi, Y., Yoo, J., Moon, J., Kim, Y., Lee, E. Y., Kim, J. G., & Hong, J.-H. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791204 · Cited by 4
“For instance, Louie et al. [59] introduced CoCoMo , an AI-assisted co-creative system that lets novice users compose melodies by iteratively refining AI suggestions.”
Human-AI Co-Creation: A New Interaction Paradigm for Human-AI Interaction
Davis, N., Clemens, M. P., Rezwana, J., & Browne, E. (2026) · Springer eBooks · doi:10.1007/978-981-95-3658-0_76 · Cited by 4
Designing Accessible Content Creation Support with Blind and Low Vision Creators
Zhang, L. (2024) · ACM SIGACCESS Accessibility and Computing · doi:10.1145/3654768.3654775 · Cited by 6
Choosing What You Want Versus Getting What You Want: An Experiment with Choice in Video Ad Placement
Hsu, S., & Karahalios, K. G. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642869 · Cited by 4
“Research highlights that providing controls improved feelings of satisfaction, transparency, and control in a variety of applications, including recommender systems [18, 22, 40], AI co-creation [29], and LLMs [42].”
BackgroundRedefining the User in Human-Generative AI Collaboration: Insights from Music Composition
Gianet, E. T., Di, L., & Rapp, A. (2024) · Institutional Research Information System University of Turin (University of Turin) · Cited by 4
Co-creative Orchestration of Angeles with Layer Scores and Orchestration Plans
Maccarini, F., Oudin, M., Giraud, M., & Levé, F. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56992-0_15 · Cited by 4
Standing on the Shoulders of Generative AI
Ch'ng, L. K. (2024) · Advances in educational technologies and instructional design book series · doi:10.4018/979-8-3693-1351-0.ch001 · Cited by 4
MIDI-Draw: Sketching to Control Melody GenerationPreprint
Namgyal, T., Flach, P. A., & Santos‐Rodríguez, R. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.11605 · Cited by 4
“Control over these features enables users to feel more self-efficacy and ownership over the generated music [9].”
BackgroundLiu, Z. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.13847 · Cited by 4
“Studies have demonstrated how AI can enhance human creativity in areas such as writing [4], drawing [21], and music composition [17], helping users achieve higher-quality outcomes.”
Panchanadikar, R., & Freeman, G. (2026) · Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790869 · Cited by 3
Lehmann, F., & Buschek, D. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3733053 · Cited by 3
“…AI prototypes studied text interaction [3, 8, 9, 18, 19, 29, 31, 42, 47], image interaction [12, 34, 46, 50, 54], visualization editing [48], creative applications with sound [33], drawing with language input [24], and the evaluation of a tool to prototype the design of AI applications [45].”
A comprehensive study on optimized neural networks for automatic piano music generation
Zhang, A., & Tian, R. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04530-9 · Cited by 3
Bryan–Kinns, N., Perry, P., Wilson, E., & Wszeborowska, A. (2025) · Springer eBooks · doi:10.1007/978-981-95-3658-0_86 · Cited by 3
Freeman, G., Mynatt, E. D., Lampe, C. A. C., Candello, H. C. D. S. P., Inkpen, K. M., & Goyal, N. (2025) · ACM Conference on Computer Supported Cooperative Work (CSCW) · doi:10.1145/3715070.3748275 · Cited by 3
“Generative Artificial Intelligence (AI) systems (e.g., ChatGPT and Midjourney) are trained using large datasets and can generate music, texts, videos, arts, and designs that are similar to what humans could create based on learned and reproduced patterns from the training datasets [14, 26].”
Keyframer: A Design Probe for Exploring LLM Assistance in 2D Animation Design
Tseng, T., Cheng, R., McNutt, A. M., & Nichols, J. W. (2025) · IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) · doi:10.1109/vl-hcc65237.2025.00014 · Cited by 3
“AI co-creation UI paradigms have been explored in domains like graphic design [2, 3, 5, 7], software development [8, 9], creative computing [10, 11], UI design [12], writing [13, 14], CAD [15, 16], and music [17].”
SoniFork: Towards Chef-AI Sound Co-Creation for Orchestrating Real-Time Auditory Dining Experiences
Wang, H., Abewickrema, S., Luo, H., Zheng, Y., Luo, S., Fang, Z., Deng, J., Elvitigala, D. S., & Mueller, F. (2025) · International Conference on Human-Engaged Computing (ICHEC) · doi:10.1145/3786995.3787073 · Cited by 3
“Especially, the advancements in AI capabilities are gradually narrowing the knowledge gap between audio experts and novices (e.g., Chefs) [28, 31], highlighting the potential of human-AI sound co-creation to further enhance creative exploration.”
DRAWBOT: Making Everyday Objects Interactive
Jain, C., Brown, H. L., & Knight, H. (2024) · ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1145/3610978.3640607 · Cited by 3
Exploration and Optimization of Generative Variability in Future Work: A Mixed-Initiative Analysis
Muller, M. J., He, J., & Weisz, J. D. (2025) · Annual Symposium on Human-Computer Interaction for Work (CHIWORK) · doi:10.1145/3729176.3729195 · Cited by 4
“Louie et al. [57] used an earlier form of generative AI to create a collection of musical passages following user requirements, and to refine selected one or sets of those passages.”
InfluentialBelibou, A., & Iftene, L. (2024) · Tehnologii informatice și de comunicație în domeniul muzical / Information and communication Technologies in Musical Field · doi:10.47809/ictmf.2024.01.05 · Cited by 3
BOUNDLESS CREATION, VIRTUAL MUSIC AND GLOBAL COLLABORATION
Justin, R. S., & Darmayuda, I. K. (2024) · Proceeding Bali-Bhuwana Waskita Global Art Creativity Conference · doi:10.31091/bbwp.v4i1.569 · Cited by 3
TAP OR SWIPE: INTERACTION'S IMPACT ON COGNITIVE LOAD AND REWARDS IN A MOBILE MENTAL MATH GAME
Jost, P., & Künz, S. R. A. A. (2023) · Cognition and Exploratory Learning in Digital Age · doi:10.33965/celda2023_202306l019 · Cited by 3
Stammer, D., Strauß, H., & Knees, P. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5738744 · Cited by 3
AI-Assisted Music Production: A User Study on Text-to-Music ModelsPreprint
Ronchini, F., Comanducci, L., Marcucci, S., & Antonacci, F. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.23364 · Cited by 3
“Several interfaces have been proposed to improve interaction between generative models and users [3,20,29,46,48,42], AI-assisted music composition [28], along with creative supporting tools designed to enhance collaborative creativity [5,11,16].”
Exploring the Collaborative Co-Creation Process with AI: A Case Study in Novice Music Production
Fu, Y., Newman, M., Going, L., Feng, Q., & Lee, J. H. (2025) · arXiv · Cited by 30
“However, previous studies have predominantly examined individual musicians’ interactions with single-purpose AI tools in controlled settings [37, 52], leaving a gap in understanding how teams of creators, particularly novices, integrate AI tools across an entire production cycle.”
Analysis of Al-generated Music Applications in Primary Schools under the STEAM Education System
Chen, S., Sun, X., Xintong, X., Shijia, T., & Yuemei, Y. (2023) · Cambridge Explorations in Arts and Sciences · doi:10.61603/ceas.v1i1.11 · Cited by 2
“Not only are these music materials not very suitable for the teaching environment of Chinese primary schools, but there are also substantial technical requirements for teachers (Louie, 2020).”
BackgroundClaveNet: Generating Afro-Cuban Drum Patterns through Data Augmentation
García, D. F., García, H. F., & Riondato, M. (2024) · Audio Mostly Conference (AM) · doi:10.1145/3678299.3678335 · Cited by 2
“There is a growing body of work focused on creating human-AI interfaces for symbolic music co-creation [17, 26, 27, 36].”
Scaling Analysis of Creative Activity Traces via Fuzzy Linkography
Smith, A., Anderson, B. R., Otto, J., Karth, I., Sun, Y., Chung, J. J. Y., Roemmele, M., & Kreminski, M. (2025) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3706599.3720184 · Cited by 2
“Recent years have seen especially strong growth in the adoption of AI-based CSTs—in creative domains as wide-ranging as writing [36], visual art [7, 45], game design [23], fashion design [28], worldbuilding [12], and music [40].”
GenFODrawing: Supporting Creative Found Object Drawing With Generative AI
Leng, J., Ye, H., Xu, P., Lam, M.-L., & Fu, H. (2025) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2025.3626754 · Cited by 2
“Sofar,existingworkshave exploredhuman-AIco-creationtopicsacrossvariousdomains, achievingnotableprogress,suchasmusic[29],video[30], [31], writing [32], [33], programming tutorials [34], sports news [35], design [36], [37], etc.”
The Case for Sustainable AI in the Creative Industry
Sowriraghavan, A. (2025) · Women in engineering and science · doi:10.1007/978-3-031-95890-8_10 · Cited by 2
Li, Y., Huang, Y., Chen, C., Liu, X., Yang, Z., & Yip, D. K. M. (2025) · International Symposium on Visual Information Communication and Interaction (VINCI) · doi:10.1145/3769534.3769545 · Cited by 2
“As art facilitates emotional self-expression through personal exploration [21], AI technologies extend creative possibilities—e.g., emotion-varying AI music and text-to-image models for artistic generation [18, 26].”
Chen, L. L., & Collins, K. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-6960-1_12 · Cited by 2
Adaptive Prompt Elicitation for Text-to-Image Generation
Wen, X., Hegemann, L., Jin, X., Ma, S., & Oulasvirta, A. (2026) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3742413.3789149 · Cited by 2
“Qualitative analysis reveals that APE’s interactive elicitation process helps users discover and articulate preferences they could not initially verbalize, suggesting that the approach not only elicits existing intent but facilitates intent formation through guided exploration [49, 63].”
Su, L.-T., Chen, U.-D., Wu, Y.-S., Chen, Y.-J., & Chang, Y.-J. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790950 · Cited by 2
“Explaining the system’s behavior and reasoning not only clarifies how user feedback informs future actions [65] but also builds trust over time [79, 91], which is essential for continued participation.”
SoundStager: Interactive Design of Story-Driven GenAI Soundscapes for Video
Yoo, S., Santisteban, A. H., Seetharaman, P., Salamon, J., Nieto, O., & Truong, A. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790870 · Cited by 2
“…turned to generative approaches, examining how text-to-music interfaces can better align with the needs of video creators [22], and how novice users steer AI-generated music to match creative intent [51], and how prompt-based music models shape users’ creative strategies and expectations [11, 59].”
The Role of Community Engagement in Promoting Mental Wellness
Taliana, L. (2023) · Interdisciplinary Journal Papier Human Review · doi:10.47667/ijphr.v4i2.267 · Cited by 2
“Whether within the form of emotional guide, instrumental assistance, or informational steerage, knowing that one isn't always alone in facing difficulties contributes to a extra experience of resilience (Louie et al., 2020).”
BackgroundDesigning Expressive Interaction with Generative Artificial Intelligence
Peng, X. (2024) · Frontiers in artificial intelligence and applications · doi:10.3233/faia240215 · Cited by 2
Music and Healthcare Recommendation Systems
Kleć, M., & Wieczorkowska, A. (2021) · Studies in computational intelligence · doi:10.1007/978-3-030-66450-3_12 · Cited by 2
MusicCollage: A Music Composition Tool for Children Based on Synesthesia and a Genetic Algorithm
Yan, G., Yao, C., Zhang, C., Wang, J., Hu, Y., & Ying, F. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-05431-0_15 · Cited by 2
Metadata
- Authors
- Louie, R., Coenen, A., Huang, C. Z., Terry, M., & Cai, C. J.
- Affiliations
- Northwestern University (US)
- Google (United States) (US)
- Independent Researcher, Mountain View, CA, USA
- Venue
- Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2020-04-21
- Pages
- 1-13
- OpenAlex
- W3031000691
- Semantic Scholar
- 77a5e08f361b6f91cac8a24b380a14c12bb93383
- Cited by
- 271
- References
- 37
- Citations by year
- 2026: 40 · 2025: 75 · 2024: 65 · 2023: 40 · 2022: 34 · 2021: 14 · 2020: 3
- FWCI
- 7.02
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- CHI Conference on Human Factors in Computing Systems (publishedVersion, cc-by-sa)
- Topics
- Social Sciences › Arts and Humanities › Music › Music Technology and Sound Studies
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Keywords
- novice users, generative music, user trust, self-efficacy, human-AI collaboration, music composition
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.