DPOAE信号时域分解算法的窗宽选择

Determination of window duration in time-domain decomposition algorithms for DPOAE

研究畸变产物耳声发射(DPOAE)产生源机制常用分解方法,针对实验分解方法干扰多、实验量大的特点,该文提出基于小波分解的互相关和基于DPOAE时域能量分布的窗宽选择算法进行时域分解。通过强化不同成分分界点,加窗提取相位特征不同的信号成分。结果与实验方法进行对比,表明算法实现了DPOAE的准确分解,其效果与实验加最佳抑制声时结果相似,同时避免了干扰、减少了实验量。该方法为DPOAE产生源机制的研究提供了更方便、准确的研究工具。

Decomposion is required in the study of the generation source mechanism of distortion product otoacoustic emissions （DPOAE）. To avoid interference and initial-experiments needed for experimental decomposing, two window-duration determination algorithms were developed to decompose DPOAE in the time-domain based on wavelet decomposition cross-correlation and another on energy distribution, The dividing point between components with different phase characteristics was enhanced by the decomposition. Different components were then extracted. Suppression experiments were conducted to verify the algorithms. The results show that the algorithms accurately decompose the DPOAE and are similar to experimental results using the best suppression tone, while eliminating interference and reducing the number of initial experiments. The method provides a more convenient, accurate way for the study of the DPOAE generation source mechanism of.