Frequency Domain Blind Separation Permutation Algorithm Based on Performance Weight Clustering

‍ ‍Although blind source separation of convolutive mixtures can be efficiently solved in the frequency domain， the problem of permutation ambiguity must be solved. A frequency domain blind separation permutation algorithm based on performance weight clustering was proposed in this paper. The algorithm used clustering to obtain the permutation reference， and calculated the accuracy of the separated signals on each frequency bin. According to the accuracy of the separation results， different frequency bins were given different clustering weights， thereby improving the reliability of the clustering results. By segmenting the frequency bins， the propagation of errors could be effectively suppressed and the performance of the algorithm was improved. Finally， several groups of simulation experiments verified the universality and performance superiority of the frequency domain blind separation permutation algorithm based on performance weight clustering， and the influence of the number of receivers on the performance of the algorithm was explored. The simulation results showed that the frequency domain blind separation sorting algorithm based on performance weight clustering can improve the signal-to-interference ratio by about 2 dB compared with the traditional amplitude correlation sorting algorithm. The more receiving antennas， the better separation performance of the algorithm.