Une ou deux composantes ? La réponse de la diffusion en ondelettes
arXiv:1905.08601
Abstract
With the aim of constructing a biologically plausible model of machine listening, we study the representation of a multicomponent stationary signal by a wavelet scattering network. First, we show that renormalizing second-order nodes by their first-order parents gives a simple numerical criterion to establish whether two neighboring components will interfere psychoacoustically. Secondly, we generalize the `one or two components' framework to three sine waves or more, and show that a network of depth suffices to characterize the relative amplitudes of the first terms in a Fourier series, while enjoying properties of invariance to frequency transposition and component-wise phase shifts.
4 pages, in French. Submitted to the GRETSI workshop