Academic Journals Database
Disseminating quality controlled scientific knowledge

Underdetermined Blind Mixing Matrix Estimation Using STWP Analysis for Speech Source Signals

ADD TO MY LIST
 
Author(s): Behzad Mozaffari Tazehkand | Mohammad Ali Tinati

Journal: Wireless Sensor Network
ISSN 1945-3078

Volume: 02;
Issue: 11;
Start page: 854;
Date: 2010;
Original page

Keywords: ICA | CWT | DWT | BSS | WPD | Laplacian Model | Expectation Maximization | Wavelet Packets | Short Time analysis | Over-complete | Blind Source Separation | Speech Processing

ABSTRACT
Wavelet packets decompose signals in to broader components using linear spectral bisecting. Mixing matrix is the key issue in the Blind Source Separation (BSS) literature especially in under-determined cases. In this paper, we propose a simple and novel method in Short Time Wavelet Packet (STWP) analysis to estimate blindly the mixing matrix of speech signals from noise free linear mixtures in over-complete cases. In this paper, the Laplacian model is considered in short time-wavelet packets and is applied to each histogram of packets. Expectation Maximization (EM) algorithm is used to train the model and calculate the model parameters. In our simulations, comparison with the other recent results will be computed and it is shown that our results are better than others. It is shown that complexity of computation of model is decreased and consequently the speed of convergence is increased.
Affiliate Program     

Tango Jona
Tangokurs Rapperswil-Jona