Learning Nonnegative Features of Spectro-Temporal Sounds for Classification

摘要

In this paper we present a method of sound classification which exploits a parts-based representation of spectro-temporal sounds, employing the nonnegative matrix factorization (NMF). We illustrate a new way of learning non-negative features using a variant of NMF and show its useful behavior in the task of general sound classification with comparison to independent component analysis (ICA) which produces holistic features.