Usually, speaker recognition systems do not take into account the short–term dependence between the vocal source and the vocal tract. A feasibility study that retains this dependence is presented here. A model of joint probability functions of the pi

基于matlab软件,的语音清音帧和浊音帧进行线性分析。-Based on the MATLAB software,on speech unvoiced frames and voiced frame using linear prediction analysis,respectively.

自动估测语音信号的基音频率。目前只能估计浊音，清音没有基音周期（会报错），基音周期取第二、三帧及以后的帧数。003和191分别是男声和女声的语音信号包。-Automatic estimation of the pitch frequency of the speech signal. Currently only estimated voiced, unvoiced no pitch (being given), take the second pitch, and after three fr

Code for unvoiced segments