Combining the modelling technique for signal with the unscented transform (UT), a new filtering algorithm is realized. It indicates by computer simulation that this new algorithm can effectively reduce noise on chaotic signal no matter how parameter of chaos generator varies with time. In comparison with the EKF algorithm, this algorithm has a better filtering performance in the case of low signal to noise (SNR), and has the similar performance in the case of high SNR. In addition, an application in blind channel equalization is also found.