Removing of audio speech signals by means of Kalman filter

Removing of audio speech signals by means of Kalman filter

Morteza Amini Sharafi1 Mohammad Saber Setoodeh Kia2 Seyede Tahere Hashemi3

1) Kermanshah Branch, Islamic Azad University, Kermanshah, Iran. Email:
2) Kermanshah Branch, Islamic Azad University, Kermanshah, Iran. Email:
3) Kermanshah Branch, Islamic Azad University, Kermanshah, Iran. Email:

IOI Code : XYCC-ABHCZ
Publication : International Conference on Science and Engineering(icesconf.com)
Abstract :
    Nowadays, multimedia (audio and video) processing is among the most important subjects discussed in engineering sciences. To apply digital filters, especially adapting filters, in the above process, are of crucial importance. Theory of adapting filters such as that of Wiener or Kalman, have been fully discussed within the continuous field, the same as in discrete-time one; in spite of this, due to the presence of computers and digital processors, the adaptable filters defiantly have more efficiency in continuous field rather than discrete-time filed. One digital filter along with an adaptable algorithm is usually applied in adaptable filters so that the filter factor can be determined by means of adaptable algorithm. In the present article the Kalman filter-which counts as one of the best filters- has been surveyed whose appropriate factors is being calculated to design a efficient filter. First of all a sample signal is randomly selected which can be the same as an Autoregressive signal. Then a merely random Gaussian noise is applied on Autoregressive signal; and consequently the noisy signal is analyzed. As soon as we analyze the noise removed. The aforesaid operation has been assimilated through the Matlab software. The results have been demonstrated as well.

Keywords : adaptive filters kalman filter gaussian noise removing the noise