基于复数平均相关调序的频域乐音盲分离

Permutation Algorithm Based on Complex Average Correlation in Frequency Domain Music Signal Blind Separation

为解决频域内卷积混合乐音盲分离存在的顺序不确定问题,提出了基于频带间复数平均相关的调序算法,对每个频带的分离子信号进行顺序调整。仿真实验结果验证了该算法的有效性,与已有的基于幅值相关和能量相关的调序方法相比,其分离性能更优。

For solving the permutation ambiguity of convoluted music blind separation in each frequency band, a permuta- tion algorithm based on average correlation of complex value is presented in this paper. Simulation results show that the algorithm is effective, and has better performance than other permutation algorithms using amplitude correlation and ener- gy correlation.