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

作　　者：金慧君[1] 宫琴[1] 陈世雄[1] 胡艳茹[1] 

机构地区：[1]清华大学生物医学工程系,北京100084

出　　处：《清华大学学报（自然科学版）》2008年第9期1515-1518,共4页Journal of Tsinghua University(Science and Technology)

基　　金：国家自然科学基金资助项目(30570472);清华-裕元医学科学研究基金项目(20240000537)

摘　　要：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.

关 键 词：畸变产物耳声发射(DPOAE) 时域分解 窗宽选择 小波分解的互相关 能量分布 

分 类 号：R319[医药卫生—基础医学]