Feature Selection and Composition using PyOracle
Greg Surges, Shlomo Dubnov · AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · 2013
A system is described which uses the Audio Oracle algorithm for music analysis and machine improvisation. Some improvements on previous Factor Oracle-based systems are presented, including automatic model calibration based on measures from Music Information Dynamics, facilities for compositional structuring and automation, and an audio-based query mode which uses the input signal to influence the output of the generative system. the ideal AO model. IR can also be used to determine the most relevant or informative audio feature at a given time. PyOracle Improviser provides some unique features for enabling composition and structured improvisations. Constraints, probabilities, and other parameters can be modified in real-time or according to a predefined script. We will discuss the use of PyOracle Improviser in a compositional context, and suggest some directions for further work in this direction.