1-3hit |
Akira IKUTA Hisako MASUIKE Mitsuo OHTA
The actual sound environment system exhibits various types of linear and non-linear characteristics, and it often contains an unknown structure. Furthermore, the observations in the sound environment are often in the level-quantized form. In this paper, a method for estimating the specific signal for stochastic systems with unknown structure and the quantized observation is proposed by introducing a system model of the conditional probability type. The effectiveness of the proposed theoretical method is confirmed by applying it to the actual problem of psychological evaluation for the sound environment.
Akira IKUTA Osman TOKHI Mitsuo OHTA
The processes observed in a sound environment inevitably contain additional external noise of arbitrary distribution. Furthermore, the actual sound environment system exhibits various types of linear and non-linear characteristics, and it often contains an unknown structure. In this paper, a method for estimating the input signal for a sound environment system with unknown structure and additive noise of arbitrary probability distribution is proposed by introducing a system model of the conditional probability type. The effectiveness of the proposed theoretical method is confirmed experimentally by applying it to the actual problem of input estimation of the sound environment.
In this study, an expression of the regression relationship with less information loss is concretely derived in the form suitable to the existence of amplitude constraint of the observed data and the prediction of response probability distribution. The effectiveness of the proposed method is confirmed experimentally by applying it to the actual acoustic data.