In fields of image processing and neural network, increasing amount of data and complex functions are making circuits precise. This makes errors in circuits relatively large. When upper bits of binary signals flip due to noise, the value will increase or decrease drastically. On the other hand, if stochastic numbers are used, the changes on their values are the same since all the bits have the same weight. Therefore, stochastic computing, a computation method based on stochastic numbers, is attracting interest. Stochastic computing does have error tolerance, but cannot restore the bit stream if the bits are erroneous. Here, we focus on evaluating the error-free value from the bit error rate and the erroneous value. We have proposed a method to correct errors of stochastic numbers by measuring the bit error rate and filtering the values properly in symmetric channels. In this paper, we propose a method that can also correct errors in Z channels as well as symmetric channels. From experimental evaluations, in environment with high bit error rate, this proposal will give a better peak-signal-to-noise ratio compared with a conventional error correction coding.