In this paper we introduce a new technique for blind source separation of speech signals. We focus on the temporal structure of the signals in contrast to most other major approaches to this problem. The idea is to apply the decorrelation method proposed by Molgedey and Schuster in the time-frequency domain. We show some results of experiments with both artificially controlled data and speech d...

Looking at the speaker s face is useful to hear better a speech signal and extract it from competing sources before identification. This might result in elaborating new speech enhancement or extraction techniques exploiting the audiovisual coherence of speech stimuli. In this paper, a novel algorithm plugging audio-visual coherence estimated by statistical tools on classical blind source separa...

This note illustrates some shortcomings of the criterion proposed in “Blind source separation based on endpoint estimation with applications to the MLSP 2006 data competition” when the number of samples is finite. This algorithm considers mutually independent sources with semibounded support, however, even for a sufficient sample size for which the finite bound of the support of the density of ...

Most of the HO blind source separation methods developed this last decade aim at blindly separating statistically independent sources, assumed stationary and ergodic. Nevertheless, in many situations such as in radiocommunications, the sources are non stationary and very often (quasi)-cyclostationary (digital modulations). In these contexts, it is important to wonder if the performance of these...

Some recent works address the problem of blind source separation with a matrix pencil. In this paper we show that the covariance matrices of the pencil can be computed at the output of a simple linear filter instead of using time-delayed covariance matrices. It is also shown, using block matrix manipulation, that the method might applied when the number of source signals is not equal to the num...

Existing perceptual models of audio quality, such as PEAQ, were designed to measure audio codec performance and are not well suited to evaluation of audio source separation algorithms. The relationship of many other signal quality measures to human perception is not well established. We collected subjective human assessments of distortions encountered when separating audio sources from mixtures...

A general approach introducing priors on the correlation function or equivalently power spectrum of the sources in the Blind Source Separation problem is presented. This prior modifies or constrains the contrast function that measures the independence of the recovered signals depending on its characteristics. Considering the case where the priors correspond to the sources that we are interested...

Abstract. We consider the Blind Source Separation problem of linear mixtures with singular matrices and show that it can be solved if the sources are sufficiently sparse. More generally, we consider the problem of identifying the source matrix S ∈ IR if a linear mixture X = AS is known only, where A ∈ IR, m 6 n and the rank of A is less than m. A sufficient condition for solving this problem is...