Implementation of Tristan Jehan's PhD thesis:
Skeleton is a set of Cocoa libraries optimized for fast development of research, and professional applications dealing with the analysis of musical signals. Based on fundamentals of psychoacoustics, perception, and learning, the underlying framework consists of machine listening, and machine learning tools, supported by flexible data structures, and visualizations.
Designed essentially to support my research as an alternative to more generic and slower tools such as Matlab, Skeleton should provide a robust, efficient, and specific, yet open programming environment for deconstructing, structuring and labeling audio, or for generating personalized music.
Skeleton aims at combining various solid scientific approaches to music listening, learning, and cognition, to enable the development of consistent creative audio applications, and enhance the music making.
Block diagram of the environment
(click for full size image)