基于MFCC和GMM的瓷砖空鼓率识别系统及方法

Ceramic tile hollow drum rate identification system and method based on MFCC and GMM

针对瓷砖因内部空鼓而引起的松动、脱落等质量问题或其他安全隐患问题,研制了一套用于瓷砖空鼓率识别的试验系统。该系统采用梅尔倒谱系数(MFCC)法提取瓷砖敲击声的特征参数,再用高斯混合模型(GMM)法对MFCC特征参数进行分类和识别。试验结果表明,采用MFCC和GMM相结合的方法,可以对瓷砖空鼓情况进行有效识别,该方法具有良好的应用前景。

In view of the quality problems such as loosening,falling off and other safety risks caused by the hollow drum inside ceramic tile,this paper developed a set of experimental system for the hollow drum rate identification of ceramic tile.The Mel-frequency cepstrum coefficient(MFCC)method was used to extract the characteristic parameters of tile knocking sound,and then the Gaussian mixture model(GMM)method was used to classify and recognize the MFCC characteristic parameters.The test results showed that the method of MFCC and GMM can effectively identify the hollow drum condition of ceramic tile,which had a good application prospect.