State estimation for sound environment system with additive external noise and state dependent noise

Abstract

In the actual situation of sound environment systems, the observed data often contain several fluctuating noises. Therefore, it is necessary to estimate the specific signal based on the observed data by introducing some noise cancellation methods. In this study, a sound environment system considering both noises of the external noise based on the additive property of energy variable and the internal noise dependent on the state variable is first paid our attention. Next, a method to estimate recursively the specific signal is derived based on Bayes' theorem in an expansion series form suitable to a signal processing with lower and higher order statistics for the observation data. Finally, the validity of the proposed method is experimentally confirmed by applying it to the actual data observed in real sound environment.