Question

求高人指点matlab语音端点检测程序

function [x1,x2] = vad(x)
%幅度归一化到[-1,1]
x = double(x);
x = x / max(abs(x));
%常数设置
FrameLen = 240;%指定帧长
FrameInc = 80;%指定帧移
amp1 = 10;
amp2 = 2;
zcr1 = 10;
zcr2 = 5;
maxsilence = 8; % 6*10ms = 30ms
minlen = 15; % 15*10ms = 150ms
status = 0;
count = 0;
silence = 0;
%计算过零率
tmp1 = enframe(x(1:end-1), FrameLen, FrameInc);%分帧处理，tmp1和tmp2为分帧后形成的二维数组
tmp2 = enframe(x(2:end) , FrameLen, FrameInc);
signs = (tmp1.*tmp2)<0;
diffs = (tmp1 -tmp2)>0.02;
zcr = sum(signs.*diffs, 2);
%计算短时能量
amp = sum(abs(enframe(filter([1 -0.9375], 1, x), FrameLen, FrameInc)), 2);
%调整能量门限
amp1 = min(amp1, max(amp)/4);
amp2 = min(amp2, max(amp)/8);
%开始端点检测
x1 = [];
x2 = [];

for n=1:length(zcr)
goto = 0;
switch status
case {0,1} % 0 = 静音, 1 = 可能开始
if amp(n) > amp1 % 确信进入语音段
x1(end+1) = max(n-count-1,1);
status = 2;
silence = 0;
count = count + 1;
elseif amp(n) > amp2 | ... % 可能处于语音段
zcr(n) > zcr2
status = 1;
count = count + 1;
else % 静音状态
status = 0;
count = 0;
if length(x1)~=length(x2)
x2(end+1)=x1(end)+count-silence/2-1;
end
end
case 2, % 2 = 语音段
if amp(n) > amp2 | ... % 保持在语音段
zcr(n) > zcr2
count = count + 1;
else % 语音将结束
silence = silence+1;
if silence < maxsilence % 静音还不够长，尚未结束
count = count + 1;
elseif count < minlen % 语音长度太短，认为是噪声
status = 0;
silence = 0;
count = 0;
else % 语音结束
status = 3;
end
end
case 3,
status=0;
x2(end+1)=x1(end)+count-silence/2-1;
end

end

% count = count-silence/2;
% v_count(i)=v_count(i)+v_count(i-1);
% v_silence(i)=v_count(i)+v_silence(i);

if length(x2)<length(x1)
x2(end+1)=length(zcr);
end

subplot(311)
plot(x)
axis([1 length(x) -1 1])
ylabel('Speech');

for i=1:length(x2);

line([x1(i)*FrameInc x1(i)*FrameInc], [-1 1], 'Color', 'red');
line([x2(i)*FrameInc x2(i)*FrameInc], [-1 1], 'Color', 'green');
end

% line([x1*FrameInc x1*FrameInc], [-1 1], 'Color', 'red');
% line([x2*FrameInc x2*FrameInc], [-1 1], 'Color', 'red');
subplot(312)
plot(amp);
axis([1 length(amp) 0 max(amp)])
ylabel('Energy');
for i=1:length(x2);
line([x1(i) x1(i)], [min(amp),max(amp)], 'Color', 'red');
line([x2(i) x2(i)], [min(amp),max(amp)], 'Color', 'green');
end
subplot(313)
plot(zcr);
axis([1 length(zcr) 0 max(zcr)])
ylabel('ZCR');
for i=1:length(x2);
line([x1(i) x1(i)], [min(zcr),max(zcr)], 'Color', 'red');
line([x2(i) x2(i)], [min(zcr),max(zcr)], 'Color', 'green');
end
具体怎么在matlab上运行

Answer 1

你把我写的这个程序运行试试，我调试通过了：
%% 该代码为基于带动量项的BP神经网络语音识别
%% 清空环境变量
clc
clear

%% 训练数据预测数据提取及归一化

%下载四类语音信号
load data1 c1
load data2 c2
load data3 c3
load data4 c4

%四个特征信号矩阵合成一个矩阵
data(1:500,:)=c1(1:500,:);
data(501:1000,:)=c2(1:500,:);
data(1001:1500,:)=c3(1:500,:);
data(1501:2000,:)=c4(1:500,:);

%从1到2000间随机排序
k=rand(1,2000);
[m,n]=sort(k);

%输入输出数据
input=data(:,2:25);
output1 =data(:,1);

%把输出从1维变成4维
for i=1:2000
switch output1(i)
case 1
output(i,:)=[1 0 0 0];
case 2
output(i,:)=[0 1 0 0];
case 3
output(i,:)=[0 0 1 0];
case 4
output(i,:)=[0 0 0 1];
end
end

%随机提取1500个样本为训练样本，500个样本为预测样本
input_train=input(n(1:1500),:)';
output_train=output(n(1:1500),:)';
input_test=input(n(1501:2000),:)';
output_test=output(n(1501:2000),:)';

%输入数据归一化
[inputn,inputps]=mapminmax(input_train);

%% 网络结构初始化
innum=24;
midnum=25;
outnum=4;

%权值初始化
w1=rands(midnum,innum);
b1=rands(midnum,1);
w2=rands(midnum,outnum);
b2=rands(outnum,1);

w2_1=w2;w2_2=w2_1;
w1_1=w1;w1_2=w1_1;
b1_1=b1;b1_2=b1_1;
b2_1=b2;b2_2=b2_1;

%学习率
xite=0.1
alfa=0.01;

%% 网络训练
for ii=1:10
E(ii)=0;
for i=1:1:1500
%% 网络预测输出
x=inputn(:,i);
% 隐含层输出
for j=1:1:midnum
I(j)=inputn(:,i)'*w1(j,:)'+b1(j);
Iout(j)=1/(1+exp(-I(j)));
end
% 输出层输出
yn=w2'*Iout'+b2;

%% 权值阀值修正
%计算误差
e=output_train(:,i)-yn;
E(ii)=E(ii)+sum(abs(e));

%计算权值变化率
dw2=e*Iout;
db2=e';

for j=1:1:midnum
S=1/(1+exp(-I(j)));
FI(j)=S*(1-S);
end
for k=1:1:innum
for j=1:1:midnum
dw1(k,j)=FI(j)*x(k)*(e(1)*w2(j,1)+e(2)*w2(j,2)+e(3)*w2(j,3)+e(4)*w2(j,4));
db1(j)=FI(j)*(e(1)*w2(j,1)+e(2)*w2(j,2)+e(3)*w2(j,3)+e(4)*w2(j,4));
end
end

w1=w1_1+xite*dw1'+alfa*(w1_1-w1_2);
b1=b1_1+xite*db1'+alfa*(b1_1-b1_2);
w2=w2_1+xite*dw2'+alfa*(w2_1-w2_2);
b2=b2_1+xite*db2'+alfa*(b2_1-b2_2);

w1_2=w1_1;w1_1=w1;
w2_2=w2_1;w2_1=w2;
b1_2=b1_1;b1_1=b1;
b2_2=b2_1;b2_1=b2;
end
end

%% 语音特征信号分类
inputn_test=mapminmax('apply',input_test,inputps);

for ii=1:1
for i=1:500%1500
%隐含层输出
for j=1:1:midnum
I(j)=inputn_test(:,i)'*w1(j,:)'+b1(j);
Iout(j)=1/(1+exp(-I(j)));
end

fore(:,i)=w2'*Iout'+b2;
end
end

%% 结果分析
%根据网络输出找出数据属于哪类
for i=1:500
output_fore(i)=find(fore(:,i)==max(fore(:,i)));
end

%BP网络预测误差
error=output_fore-output1(n(1501:2000))';

%画出预测语音种类和实际语音种类的分类图
figure(1)
plot(output_fore,'r')
hold on
plot(output1(n(1501:2000))','b')
legend('预测语音类别','实际语音类别')

%画出误差图
figure(2)
plot(error)
title('BP网络分类误差','fontsize',12)
xlabel('语音信号','fontsize',12)
ylabel('分类误差','fontsize',12)

%print -dtiff -r600 1-4

k=zeros(1,4);
%找出判断错误的分类属于哪一类
for i=1:500
if error(i)~=0
[b,c]=max(output_test(:,i));
switch c
case 1
k(1)=k(1)+1;
case 2
k(2)=k(2)+1;
case 3
k(3)=k(3)+1;
case 4
k(4)=k(4)+1;
end
end
end

%找出每类的个体和
kk=zeros(1,4);
for i=1:500
[b,c]=max(output_test(:,i));
switch c
case 1
kk(1)=kk(1)+1;
case 2
kk(2)=kk(2)+1;
case 3
kk(3)=kk(3)+1;
case 4
kk(4)=kk(4)+1;
end
end

%正确率
rightridio=(kk-k)./kk

追问

我的是语音端点检测，从论坛上找的都是这个程序，想知道具体怎么在matlab上运行

Answer 2

将上面的代码保存为vad.m文件，然后再命令窗口中调用。如：
[x,fs]=wavread('E:\a007.wav');
[x1,x2] = vad(x);