Algorithmic Audio Mashups and Synthetic Soundscapes Employing Evolvable Media Repositories

Abstract

The paper describes a metacreative system for real time algorithmic composition of audio mashups and synthetic soundscapes that pivots on evolvable media repositories, i.e., local pools of related media content that are retrieved, and ever-renovated, over the WWW in an evolutionary fashion. The model also involves a sophisticated soundscape generator, a context aware composer to parametrise it, and a machine listening module performing onset detection and spectral profiling in non-real time. The soundscape generator relies on pattern-based generators to spawn complex and contingent audio sequences in both deterministic and nondeterministic fashions, and is also capable of refined 3D acoustic spatialisation—and multi-channel rendering—with respect to virtual listeners and sonic sources.