Probabilistic Machine Listening for Interactive Music Performance Systems
Ali Cemgil and Ben Kröse
In: Machine Learning Meets the User Interface, 12 December 2003, Whistler, Canada.

Abstract

Consider the following scenario: a performer is improvising freely on a musical instrument. A computer processes the audio input, extracts high level information including the pitch, tempo and expressive characteristics and responds to the performance in a musically meaningful way. Our aim in this work is to consider a computational framework to move us closer to the realisation of such a scenario.

Postscript (Slides) - Requires a viewer, such as GhostView

[Edit]