基于duffing随机共振的说话人特征提取方法

摘要

说话人特征参数的提取直接影响识别模型的建立,MFCC与LPC参数提取方法,分别以局域低频信息和全局AR信号为主要特征.提出一种基于duffing随机共振的说话人频谱特征提取方法.仿真结果表明,该方法能识别说话人之间频谱的微小差别,有效地提取说话人频谱的基本特征,从而为说话人识别模型提供更为精细的识别模型.%Speaker feature parameter extraction directly affects the establishment of recognition model. Parameterrnextraction methods of MFCC and LPC, respectively regard local low-frequency information and global AR signal asrnthe main feature. In this paper, a method of speaker spectrum feature extraction based on duffing stochastic resonancernis proposed. Simulation results show that this method, which provides a more elaborate recognition model for speakerrnrecognition, can identify tiny differences of spectrum among speakers and extract basic characteristics of spectrumrneffectively.