Acoustic vector sensor based speech source separation with mixed Gaussian-Laplacian distributions

Abstract

Abstract-Acoustic vector sensor (AVS) based convolutive blind source separation problem has been recently addressed under the framework of probabilistic time-frequency (T-F) masking, where both the DOA and the mixing vector cues are modelled by Gaussian distributions. In this paper, we show that the distributions of these cues vary with room acoustics, such as reverberation. Motivated by this observation, we propose a mixed model of Laplacian and Gaussian distributions to provide a better fit for these cues. The parameters of the mixed model are estimated and refined iteratively by an expectation-maximization (EM) algorithm. Experiments performed on the speech mixtures in simulated room environments show that the mixed model offers an average of about 0.68 dB and 1.18 dB improvements in signal-to-distotion (SDR) over the Gaussian and Laplacian model, respectively. Index Terms-Acoustic vector sensor, mixed model, direction of arrival, EM algorithm, blind source separation.

Theoretical Analysis of Open Spherical Microphone Arrays for Acoustic Intensity Measurements

“…The particle velocity is then given as: (9) Defining the unit vector from the point on the surface in the direction of the estimation point, , as , the following expressions can be given:…”

“…Apart from its primary use in measuring the acoustic power and the sound radiation [1], active intensity has also been used as a basis for sound source localization [4], [5], [6], source separation [7], [8], [9] and spatial audio coding [10], [11]. These tasks require the accurate measurement of acoustic intensity.…”