%0 Journal Article
%T 病理语音的S变换特征<br>S transform feature for pathological speech
%A 李海峰
%A 房春英
%A 马琳
%A 张满彩
%A 孙佳音
%J 清华大学学报（自然科学版）
%D 2016
%R 10.16511/j.cnki.qhdxxb.2016.21.042
%X 病理语音具有强烈的非平稳性和突变性特点，较难分析。S变换具有良好的时频分辨率和时频定位能力。该文将S变换与人耳听觉的Mel特性结合，提出一种能够突出发声器官病变的病理语音特征MSCC（Mel S-transform cepstrum coefficients）。在NCSC语料库上，通过与经典语音倒谱特征MFCC （Mel frequency cepstrum coefficients）和当前常用声学特征的对比，表明MSCC特征对语音中动态、快变的病理信息具有更强的刻画能力。此外，选用F-Score方法对特征进行评价和采用粒子群算法进行特征筛选，MSCC表现出了更好的分类性能。可见，MSCC特征可以为临床诊断提供病理语音的高精准分析。<br>Abstract：Pathological speech is difficult to analyze because it is non-stationary and mutative. The study combines the S transform, which has good time-frequency resolution and time-frequency positioning capability with the human auditory Mel characteristics to calculate Mel S-transform cepstrum coefficients (MSCC) which highlight vocal organ pathological lesions. The MSCC are compared with the classical Mel frequency cepstrum coefficients (MFCC) and the common acoustic characteristics in the NCSC corpus to show that the MSCC are more able to portray the dynamics and to quickly identify pathological speech information. In addition, the MSCC also give classification performance based on the F-Score method with the particle swarm optimization algorithm for feature selection. Therefore, the MSCC provide accurate analyses of pathological speech characteristics for clinical diagnosis.
%K 病理语音
%K S变换
%K Mel倒谱
%K MSCC特征
%K &lt
%K br&gt
%K pathological speech
%K S transform
%K Mel cepstrum
%K Mel S-transform cepstrum coefficients (MSCC) feature
%U http://jst.tsinghuajournals.com/CN/Y2016/V56/I7/765