Project: Qualitative Inquiry on Machine learning in Musical Performance

As in many artistic sectors, Machine Learning (ML) has also become part of music performance practice, although still little studied. Such inquiry can provide important insights into modes of expression and interaction, and their collective practice as a community. We conducted an interview study with 14 musical artists about their relationship with ML. We first find that artists developed new interaction strategies with ML to enable musical agency, by familiarizing themselves with the technology, control its behavior and explore its limits into live performances. This strategies are developed through data curation, real-time interaction and long-term practice. Secondly, artists have a practice of remixing and assembling musical material that extends to the collective level through the sharing of knowledge and content. Drawing from our findings, we discuss how artistic community provide knowledge to support new forms of interaction with ML.

See our published papers at the conference NIME 2023:

Machine Learning for Musical Expression: A Systematic Literature Review

Culture and Politics of Machine Learning in NIME: A Preliminary Qualitative Inquiry

For more details, see the following preprint: