In order to segment accurately and on-line,most conventional algorithms are based on small-scale audio classification and always result in a high false segmentation rate.
目前大多数传统的音频流分割方法是基于小尺度音频分类的,但是这类分割方法普遍存在虚假分割点过多的缺点,严重影响了实际应用的效果。
First, this paper analyzes many simulative signals by Matlab, and thendiscusses the problem of illusive component due to HHT , uses the K-S test to recognise theillusive component, proposes the similarity probability between the IMFs and the signal as thestandard that whether a IMF is illusive or not, and gets t.
本文首先在Matlab平台上应用HHT理论对大量的仿真信号进行了深入分析,并针对HHT产生虚假分量的问题,提出应用K-S拟合优度检验理论进行虚假分量识别,以分解后各个固有模态分量(IMF)与原始信号之间的相似概率作为判断标准,识别和去除虚假分量。
