The correlated noise reducing model using a kalman filter for speech vector quantization

The kalman filter is a recursive predictive filter that is based on the use of state space techniques and recursive algorithms. The advantage of kalman filter is, it estimates the state of dynamic system which can be disturbed by some noise. Thus this article presents the correlated noise reducing model using a kalman filter for speech vector quantization. The Q and R covariance constant parameters are investigated to provide the optimal performance with minimum noise of speech vector quantization signal. The results show that this model provides the minimum error as 1.0023 and 0.3622 for measurement error covariance and estimatation error covariance respectively.