Pathological voice detection device based on improved autocorrelation characteristics

The invention relates to the technical field of pathological voice detection. A pathological voice detection device based on improved autocorrelation characteristics comprises a microphone, a computer, a display screen and a loudspeaker box. Voice is collected through the microphone to serve as input data, the input data is processed in the computer, and then a classification result and classification accuracy are output through the display screen and the loudspeaker box. Compared with the traditional Mel-frequency cepstrum coefficient, rhythm, formant and other characteristics, the improved autocorrelation characteristic provided by the invention can well analyze the nonlinear characteristic of the voice, can represent the voice characteristics of different frequency bands, and has a better detection effect than the traditional characteristic. 本发明涉及病理语音检测技术领域。一种基于改进自相关特征的病理语音检测装置，包括话筒、计算机、显示屏和音箱，通过话筒收集语音作为输入数据，输入数据在计算机内进行处理然后通过显示屏和音箱输出分类结果和分类准确率。相比于传统的梅尔倒谱系数、韵律、共振峰等特征，本发明提出的改进自相关特征能较好地对语音的非线性特性进行分析，并且可以表示出不同