1. Principle:

The short-term average zero-crossing rate indicates the number of times the speech signal waveform crosses the horizontal axis in a frame of speech

Two, calculate the zero-crossing rate code

clear all; clc; close all;
filedir=[];                       % Set path
filename='bluesky3.wav';          %  Set file name
fle=[filedir filename];           %  Compose the complete path and file name
[xx,Fs]=audioread(fle);             %  Read in the data file
x=detrend(xx);                    %  Eliminate DC component
wlen=200; inc=80;                 %  Set frame length, frame shift
win=hanning(wlen);                %  Window function
N=length(x);                      %  Find the data length
X=enframe(x,win,inc)';            %  Framing
fn=size(X,2);                     %  Get the number of frames
zcr1=zeros(1,fn);                 %  Initialize
for i=1:fn
    z=X(:,i);                     %  Get a frame of data
    for j=1: (wlen-1);          %  Find zero crossings in one frame
         if z(j)* z(j+1)< 0       %  Determine whether it is a zero-crossing point
             zcr1(i)=zcr1(i)+1;   %  Is the zero crossing point, record1Times
         end
    end
end
time=(0:N-1)/Fs;                  %  Calculate time coordinate
frameTime=frame2time(fn,wlen,inc,Fs);  %  Find the time corresponding to each frame
%  Drawing
subplot 211; plot(time,x,'k'); grid;
title('Speech waveform');
ylabel('Amplitude'); xlabel(['Time/s' 10 '(a)']);
subplot 212; plot(frameTime,zcr1,'k'); grid;
title('Short-term average zero-crossing rate');
ylabel('Amplitude'); xlabel(['Time/s' 10 '(b)']);

The short-time average zero-crossing rate can be used to find the voice signal from the background noise, which can be used to determine the start and end positions of the silent and no-talk segments.