Abstract
To better support creative software developers and music technologists' needs, and to empower them as machine learning users and innovators, the usability of and developer experience with machine learning tools must be considered and better understood. We review background research on the design and evaluation of application programming interfaces (APIs), with a focus on the domain of machine learning for music technology software development. We present the design rationale for the RAPID-MIX API, an easy-to-use API for rapid prototyping with interactive machine learning, and a usability evaluation study with software developers of music technology. A cognitive dimensions questionnaire was designed and delivered to a group of 12 participants who used the RAPID-MIX API in their software projects, including people who developed systems for personal use and professionals developing software products for music and creative technology companies. The results from questionnaire indicate that participants found the RAPID-MIX API a machine learning API which is easy to learn and use, fun, and good for rapid prototyping with interactive machine learning. Based on these findings, we present an analysis and characterization of the RAPID-MIX API based on the cognitive dimensions framework, and discuss its design trade-offs and usability issues. We use these insights and our design experience to provide design recommendations for ML APIs for rapid prototyping of music technology. We conclude with a summary of the main insights, a discussion of the merits and challenges of the application of the CDs framework to the evaluation of machine learning APIs, and directions to future work which our research deems valuable.
Highlights
Research on the design of music systems with artificial intelligence techniques goes back more than 30 years (Dannenberg, 1985)
We provide a set of recommendations for the design of machine learning (ML) application programming interfaces (APIs) for prototyping music technology
We adopted a deductive analytical approach in which we used codes based on the Cognitive Dimensions (CDs) framework and on the higher-level themes of Table 2, and on an auto-encoding analysis performed with NVivo
Summary
Research on the design of music systems with artificial intelligence techniques goes back more than 30 years (Dannenberg, 1985). Usability of Machine Learning APIs interactive machine learning (IML)—i.e., using supervised machine learning (ML) for mapping between different kinds of inputs (e.g., sensor data, motion descriptors, audio features) and parameters of sound and music processes (e.g., Fiebrink et al, 2011; Françoise et al, 2013; Caramiaux et al, 2014)— has uncovered very meaningful advantages. They include, for instance, workflows with increased celerity and ease-of-use, intuitive exploration of complex mappings and high-dimensional parameter spaces, and increased utility of small training data sets. In order to facilitate the adoption of ML by music and creative software developers, the usability and the developer experience with new tools for designing, developing and using ML, must be considered and better understood
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
