Conference paper Open Access
Bernardo, Francisco; Kiefer, Chris; Magnusson, Thor
The growing popularity of the live coding and algorave scenes has inspired incentive and support for accessible, diverse and innovative approaches in expressing art through code. With live coding, the real-time composition of music and other art becomes a performance art by centering on the language of the composition itself, the code.
Sema is a new open source system which aims to support user-friendly approaches to language design and machine learning in live coding practice. This paper reports on the latest technical advances and user research with Sema.
We provide an overview and design rationale for the early technical implementation of Sema, including technology stack, architecture, user interface, integration of machine learning, and documentation and community resources. We also describe the activities of the MIMIC Artist Summer workshop, a full-week workshop with a group of 12 participants, which we designed and delivered to gather user feedback about the first design iteration of Sema.
Findings from our workshop corroborate that language design and machine learning are advanced topics in computer science which may be challenging to users without such a background. Nevertheless, we found that such topics can inform the design of systems which may be both useful and usable to the live coding community.