A tutorial on nonstationarity detection in acoustic signals: Parametric and nonparametric approaches.

Abstract

This tutorial provides an overview of nonstationarity detection in acoustic signals, focusing on model‐based parametric approaches as well as more flexible nonparametric ones. The techniques discussed are presented in the context of speech and audio waveforms, with several real‐world examples given, but also apply more broadly to any class of acoustic signals that exhibits locally stationary behavior. Many such waveforms, in particular information‐carrying natural sound signals, exhibit a degree of controlled nonstationarity, and are often well modeled as slowly time‐varying systems. The tutorial first describes the basic concepts of such systems and their analysis via local Fourier methods. Parametric approaches appropriate for speech are then introduced by way of time‐varying linear predictive models, along with nonparametric approaches based on variation of time‐localized estimates of the power spectral density of an observed random process. [Work supported in part by DARPA, NGA, and NSF.]