The midway assessment is organised in two parts, and starts with a two-hour public seminar, followed by a closed meeting.
The purpose of the midway assessment is to evaluate the progress of the PhD project at a point when it is still possible to make small or more substantial changes.
You can also participate on Zoom here.
Programme
10:15 - 10:40 Welcome, and Presentation by Candidate Vincenzo Madaghiele.
10:45 - 11:45 Comments by, and discussion with Dr. Oliver Bown.
11:45 - 12:00 Plenary discussion with the public
Following the public event, there will be a closed meeting between the candidate, invited opponent, and supervisors (12:00 - 12:30).
Title
Improvising machines: Autonomous agents and listening-based control strategies for music co-improvisation
Summary
Music improvisation requires listening, reflection and timely decision-making. When improvising together, musicians make decisions in time, responding to other musicians' ideas, their style and the musical context of the performance. Musical agents are algorithms that, when integrated in interactive music systems, can tackle one or more creative tasks. In doing so, agents can automate functions that imply aesthetic decisions. Automating musical decisions can provide novel possibilities for artistic expression, however to contribute to music in a meaningful way, agents' behaviors must adhere to musicians' aesthetic goals, which can be expressed explicitly or implicitly, and can be more or less abstract.
This thesis investigates music co-creation between humans and autonomous artificial agents in free improvisation, focusing on agents' context-awareness and the possibility of expressing behaviors towards specific aesthetic goals. The thesis presents the design of a set of live algorithms for co-improvisation for varied musical scenarios, based on small curated corpora, machine listening and integration with environments for real-time music programming. By employing a combination of formal modeling, iterative design and evaluation, and practice-based research, the thesis investigates autonomous decision-making in improvised music from musicians’ perspectives. What characteristics should an artificial agent have to coherently complement human creativity in an improvised musical performance? How can autonomous decision-making extend human possibilities in music improvisation?
Bio
Vincenzo is a doctoral researcher at the department of musicology, University of Oslo. He has a background in media engineering and machine learning, with applications to new media and experimental music. His PhD project investigates the design of artificial musical agents for performance and improvisation from a technical and aesthetic point of view. He is a musician and sound artist, developing performances and installations based on interactive systems and algorithmic music.