基于联合加权的广义二次相关时延估计算法

Generalized Secondary Correlation Delay Estimation Algorithm Based on Joint Weighting

现有的时延估计算法在低信噪比条件下时延估计值与真实值误差较大,而时延估计的准确性直接影响声源定位的最终结果,于是提出一种联合加权的广义二次相关时延估计算法。通过在已有的广义二次相关算法的基础上,对其加权函数进行改进,联合相位变换(PHAT)和平滑相干变换(SCOT)函数,得到新的广义加权函数:SCOT/PHAT。在MATLAB中设计了基于麦克风阵列的时延估计和声源定位的仿真,并与传统的PHAT加权和基于广义二次相关的SCOT加权算法对比,结果表明,在低信噪比环境下,改进算法能得到较高的时延估计精度。

The existing time delay estimation algorithms have a large error between the estimated value of time delay and the real value under the condition of low SNR,and the accuracy of time delay estimation directly affects the final result of acoustic source location.Therefore,a joint weighted generalized quadratic correlation time delay estimation algorithm is proposed..Based on the existing generalized secondary correlation algorithm,a new generalized weighting function,SCOT/PHAT,was obtained by improving its weighting function and combining phase transform(PHAT)and smooth coherence transform(SCOT).The simulation experiments of time delay estimation and sound source location based on microphone array were designed using MATLAB,and compared with the traditional PHAT weighted algorithm and SCOT weighted algorithm based on generalized secondary correlation.The results show that the improved algorithm can obtain higher time delay estimation accuracy in low SNR environment.