论文部分内容阅读
本文通过对咳嗽声特性的分析,在对咳嗽声进行预处理后,提取咳嗽的Mel频率倒谱系数作为特征参数,建立咳嗽模板库。采用基于动态时间规整算法的模板匹配方法对特定人的孤立咳嗽进行识别,实验证明,通过将咳嗽声的特性和语音识别方法的结合,动态时间规整算法在对孤立咳嗽声识别中有很好的准确性和可靠性。
In this paper, through the analysis of the characteristics of cough, after the cough sound pretreatment, the Mel frequency Cepstral coefficient of cough was extracted as the characteristic parameters to establish a cough template library. The template matching method based on the dynamic time warping algorithm is used to identify the isolated cough of a particular person. Experiments show that the dynamic time warping algorithm has good performance in isolated cough sound recognition by combining the characteristics of the cough sound and the voice recognition method Accuracy and reliability.