This page proposes to explore a work in progress that aims at developing a computer-aided-composition approach to structuring music by means of audio clustering and graph search algorithms. Although parts of this idea have been investigated in order to achieve different tasks such as corpus-based concatenative synthesis [Schwartz 2006], musical genre recognition [Peeters 2007] or computer-aided orchestration [Carpentier 2008] to name a few, the challenge remains to find a way of integrating these techniques into the creative process; not to generate material but to explore, to analyse and to understand the full potential of a given sound corpus prior to scoring a musical piece. As opposed to mainstream CAC approaches, mostly focusing on generative methods, the following one proposes an analytical perspective to structuring music through the creative process.
Software (demo standalone)
Forum (group discussion)
Audio Example (transaural rendering)
N.B. This example was done using the demo standalone only!
N.B. See the slideshow pp. 21-23 for more info on how the clusters and the sounds are sequenced…