Underdetermined blind separation of speech signals with delays in different time-frequency domains

Authors:
Alessandro Bastari;Stefano Squartini;Francesco Piazza
Affiliations:
Dipartimento di Elettronica, Intelligenza Artificiale e Telecomunicazioni-Università, Politecnica delle Marche, Ancona, Italy;Dipartimento di Elettronica, Intelligenza Artificiale e Telecomunicazioni-Università, Politecnica delle Marche, Ancona, Italy;Dipartimento di Elettronica, Intelligenza Artificiale e Telecomunicazioni-Università, Politecnica delle Marche, Ancona, Italy
Venue:
Nonlinear Speech Modeling and Applications
Year:
2005

Citing 12
Cited 2

A Theory for Multiresolution Signal Decomposition: The Wavelet Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Blind separation of sources, Part 1: an adaptive algorithm based on neuromimetic architecture

Signal Processing
Ten lectures on wavelets

Ten lectures on wavelets
Wavelets and subband coding

Wavelets and subband coding
An information-maximization approach to blind separation and blind deconvolution

Neural Computation
Separation of sources: a geometry-based procedure for reconstruction of n-valued signals

Signal Processing
Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications

Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications
Natural Gradient Learning for Over-and Under-Complete Bases in ICA

Neural Computation
A Wavelet Tour of Signal Processing, Third Edition: The Sparse Way

A Wavelet Tour of Signal Processing, Third Edition: The Sparse Way
Localization of the complex spectrum: the S transform

IEEE Transactions on Signal Processing
Blind separation of speech mixtures via time-frequency masking

IEEE Transactions on Signal Processing
Entropy-based algorithms for best basis selection

IEEE Transactions on Information Theory - Part 2

Gaussianization Based Approach for Post-Nonlinear Underdetermined BSS with Delays

ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks, Part III
Some notes on nonlinearities of speech

Nonlinear Speech Modeling and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper is devoted to the problem of speech signal separation from a set of observables, when the mixing system is underdetermined and static with unknown delays. The approaches appeared in the literature so far have shown that algorithms based on the property of sparsity of the original signals (effectively satisfied by speech sources) can be successfully applied to such a problem, specially if implemented in the time-frequency domain. Here, a survey on the usage of different time-frequency transforms within the already available three-step procedure for the addressed separation problem is carried out. The novelty of the contribution can be seen from this perspective: Wavelet, Complex Wavelet and Stockwell Transforms are the new transforms used in our problem, in substitution of the usual Short Time Fourier Transform (STFT). Their performances are analyzed and compared to those attainable through the STFT, evaluating how much different is the influence that their sparseness and spectral disjointness properties on the algorithm behavior.