Elementary Sources: Latent Component Analysis for Music Composition

Complexity of music audio signals creates an access problem to specific musical objects or structures within the source samples. Instead of employing more commonly used audio analysis or production techniques to access features, we describe extraction of sub-mixtures from real-world audio using a Probabilistic Latent Component Analysis-based decomposition tool for music composition. This is highlighted with the presentation of a prior relevant compositional approach named Spectral Music along with a discussion of five compositions extending these principles using methods more commonly associated with source separation research.