2026
Matthew Peachey
Investigating Continuous Interactions for generative Tools in the Context of Musical Creativity PhD Thesis
Dalhousie University, 2026.
Abstract | BibTeX | Tags: continuous interaction, continuous-interaction-and-machine-learning, control mapping, creativity support tools, digital musical instruments, machine learning, music, sound & music computing
@phdthesis{Peachey2026b,
title = {Investigating Continuous Interactions for generative Tools in the Context of Musical Creativity},
author = {Matthew Peachey},
year = {2026},
date = {2026-10-19},
urldate = {2026-10-19},
school = {Dalhousie University},
abstract = {This thesis investigates continuous interaction as a design principle for Artificial Intelligence (AI)-powered music creativity support tools. Discrete text prompting, the de facto standard for current generative AI systems, can limit musicians’ sense of artistic agency and creative ownership. Continuous interaction instead can enable fine-grained, real-time control over the generative process, helping musicians retain a sense of authorship over the generated output.
This thesis presents three studies that together examine how continuous interaction, integrated into real-time interfaces, can better support musicians’ creative workflows. First, I derived low-dimensional latent representations from a Variational Autoencoder with an intentionally small latent space, integrated them into a real-time GUI, and evaluated them in a mixed-methods study with both novice and experienced synthesizer users (n = 18). Second, I interviewed experienced musicians (n = 10) about their hesitations toward generative AI; their concerns centered on a lack of compelling tools and workflows, further motivating continuous interaction as a design preference. Finally, I developed a framework for Aging Digital Musical Instruments (AgingDMIs), a novel class of instruments that adapt to a user’s play style over time. I then implemented a hardware prototype instantiating one point in the AgingDMI design space, and evaluated it longitudinally with experienced musicians (n= 4) for twelve recurring sessions over several weeks.
The findings presented in this thesis suggest that integrating continuous interaction into generative AI-powered creativity support tools increases musicians’ artistic agency and creative ownership and fits better within their existing creative workflows. I further contribute a validated
design framework for AgingDMIs, a novel class of adaptive and personalized digital musical instruments, and a hardware prototype that together demonstrate the principles of that framework in practice.},
keywords = {continuous interaction, continuous-interaction-and-machine-learning, control mapping, creativity support tools, digital musical instruments, machine learning, music, sound & music computing},
pubstate = {published},
tppubtype = {phdthesis}
}
This thesis investigates continuous interaction as a design principle for Artificial Intelligence (AI)-powered music creativity support tools. Discrete text prompting, the de facto standard for current generative AI systems, can limit musicians’ sense of artistic agency and creative ownership. Continuous interaction instead can enable fine-grained, real-time control over the generative process, helping musicians retain a sense of authorship over the generated output.
This thesis presents three studies that together examine how continuous interaction, integrated into real-time interfaces, can better support musicians’ creative workflows. First, I derived low-dimensional latent representations from a Variational Autoencoder with an intentionally small latent space, integrated them into a real-time GUI, and evaluated them in a mixed-methods study with both novice and experienced synthesizer users (n = 18). Second, I interviewed experienced musicians (n = 10) about their hesitations toward generative AI; their concerns centered on a lack of compelling tools and workflows, further motivating continuous interaction as a design preference. Finally, I developed a framework for Aging Digital Musical Instruments (AgingDMIs), a novel class of instruments that adapt to a user’s play style over time. I then implemented a hardware prototype instantiating one point in the AgingDMI design space, and evaluated it longitudinally with experienced musicians (n= 4) for twelve recurring sessions over several weeks.
The findings presented in this thesis suggest that integrating continuous interaction into generative AI-powered creativity support tools increases musicians’ artistic agency and creative ownership and fits better within their existing creative workflows. I further contribute a validated
design framework for AgingDMIs, a novel class of adaptive and personalized digital musical instruments, and a hardware prototype that together demonstrate the principles of that framework in practice.
This thesis presents three studies that together examine how continuous interaction, integrated into real-time interfaces, can better support musicians’ creative workflows. First, I derived low-dimensional latent representations from a Variational Autoencoder with an intentionally small latent space, integrated them into a real-time GUI, and evaluated them in a mixed-methods study with both novice and experienced synthesizer users (n = 18). Second, I interviewed experienced musicians (n = 10) about their hesitations toward generative AI; their concerns centered on a lack of compelling tools and workflows, further motivating continuous interaction as a design preference. Finally, I developed a framework for Aging Digital Musical Instruments (AgingDMIs), a novel class of instruments that adapt to a user’s play style over time. I then implemented a hardware prototype instantiating one point in the AgingDMI design space, and evaluated it longitudinally with experienced musicians (n= 4) for twelve recurring sessions over several weeks.
The findings presented in this thesis suggest that integrating continuous interaction into generative AI-powered creativity support tools increases musicians’ artistic agency and creative ownership and fits better within their existing creative workflows. I further contribute a validated
design framework for AgingDMIs, a novel class of adaptive and personalized digital musical instruments, and a hardware prototype that together demonstrate the principles of that framework in practice.
2025
Matthew Peachey; Sageev Oore; Joseph Malloch
Evaluating Low-Dimensional Latent Representations as a Creative Interface for Digital Synthesizers Proceedings Article
In: The Conference on AI Music Creativity (AIMC), 2025.
Links | BibTeX | Tags: continuous interaction, continuous-interaction-and-machine-learning, machine learning, music
@inproceedings{Peachey2025,
title = {Evaluating Low-Dimensional Latent Representations as a Creative Interface for Digital Synthesizers},
author = {Matthew Peachey and Sageev Oore and Joseph Malloch},
url = {https://zenodo.org/records/16946459},
year = {2025},
date = {2025-09-10},
urldate = {2025-09-10},
booktitle = {The Conference on AI Music Creativity (AIMC)},
keywords = {continuous interaction, continuous-interaction-and-machine-learning, machine learning, music},
pubstate = {published},
tppubtype = {inproceedings}
}
2022
Muhammad Raza; Derek Reilly; Joseph Malloch
Active Visualization of Visual Cues on the Hand for Better User Interface Design Generalization in Mixed Reality Proceedings Article
In: Proceedings of the 5th IEEE International Conference on Artificial Intelligence & Virtual Reality (AIVR 2022), Late-Breaking Work, pp. 149–152, IEEE, 2022.
Links | BibTeX | Tags: continuous interaction, embodied interaction, feedforward, mixed reality, natural user interface
@inproceedings{Raza2022,
title = {Active Visualization of Visual Cues on the Hand for Better User Interface Design Generalization in Mixed Reality},
author = {Muhammad Raza and Derek Reilly and Joseph Malloch},
doi = {10.1109/AIVR56993.2022.00030},
year = {2022},
date = {2022-12-12},
urldate = {2022-12-12},
booktitle = {Proceedings of the 5th IEEE International Conference on Artificial Intelligence & Virtual Reality (AIVR 2022), Late-Breaking Work},
pages = {149--152},
publisher = {IEEE},
keywords = {continuous interaction, embodied interaction, feedforward, mixed reality, natural user interface},
pubstate = {published},
tppubtype = {inproceedings}
}
2018
Joseph Malloch
Toward Rich, Continuous Representation and Interaction Conference
Workshop on Rethinking Interaction, ACM SIGCHI Conference on Human Factors in Computing Systems (CHI 2018), ACM Montreal, Canada, 2018.
Abstract | BibTeX | Tags: continuous interaction, continuous representations
@conference{Malloch2018_CHI_Workshop,
title = {Toward Rich, Continuous Representation and Interaction},
author = {Joseph Malloch},
year = {2018},
date = {2018-04-21},
booktitle = {Workshop on Rethinking Interaction, ACM SIGCHI Conference on Human Factors in Computing Systems (CHI 2018)},
address = {Montreal, Canada},
organization = {ACM},
abstract = {I present a suggestion for rethinking some common assumptions when designing interactive systems. In brief, I advocate that developers exercise restraint before perform- ing classification or identification steps when processing human input to a system, and consider carefully a) whether classification is necessary or desirable for the interaction; b) whether a continuous representation might be prefer- able in terms of computational efficiency, user efficiency, or user experience; and finally c) in cases where classification/identification is the appropriate approach, whether it might be useful to augment and enrich the discrete, classified objects with continuous data representations.},
keywords = {continuous interaction, continuous representations},
pubstate = {published},
tppubtype = {conference}
}
I present a suggestion for rethinking some common assumptions when designing interactive systems. In brief, I advocate that developers exercise restraint before perform- ing classification or identification steps when processing human input to a system, and consider carefully a) whether classification is necessary or desirable for the interaction; b) whether a continuous representation might be prefer- able in terms of computational efficiency, user efficiency, or user experience; and finally c) in cases where classification/identification is the appropriate approach, whether it might be useful to augment and enrich the discrete, classified objects with continuous data representations.