Ikuta A., Ohta M.

The observation data in actual sound environment system exhibit various types of fluctuation characteristics, and these often contain uncertainty. For example, the observed signal is inevitably contaminated by the additional external noise (i.e., background noise) of arbitrary distribution type with unknown statistics. In this situation, in order to evaluate the specific signal based on the observed noisy data, it is indispensable to introduce a unified state estimation method. Though several state estimation methods have been proposed up to now, these state estimation algorithms have been realized by introducing the additive model of the specific signal and the external noise under an assumption of known statistics of the external noise. The observation equation in sound environment can be generally expressed in an additive model on the specific signal and the background noise in energy scale by using physically the additive property of acoustic energy. However, there exists complex nonlinear relationship between the noise evaluation quantities of the specific signal and the background noise, and it is difficult in general to find a functional relationship between them. Furthermore, it is actually difficult to know in advance statistical properties of the background noise. In this study, a state estimation method for a specific signal under the existence of a background noise with unknown statistical properties is proposed in a form without considering the usual additive model. More specifically, after introducing a membership function for uncertainty of a sound environment system, by applying a fuzzy inference for a relationship between the observed data and the specific signal, a state estimation algorithm is derived. The effectiveness of the proposed method is experimentally confirmed by applying it to the estimation of noise evaluation quantities for road traffic noise under existence of a background noise.