语音信号特征提取程序设计代码

精心设计的基于MATLAB的代码设计

主程序：

%

fs=22050; %抽样频率 x=wavread('2.wav');

figure(1);subplot(211);plot(x);

title('原始语音信号波

形','fontsize',16,'fontweight','bold'); xlabel('样点数

','fontsize',16,'fontweight','bold');

ylabel('幅值','fontsize',16,'fontweight','bold');grid on; N=128; n=0:N-1; y=fft(x); mag=abs(y);

f=(0:length(y)-1)'*fs/length(y);%进行对应的频率转换

figure(1);subplot(212);plot(f,mag);

title('原始信号频谱图','fontsize',16,'fontweight','bold'); xlabel('频率（Hz）','fontsize',16,'fontweight','bold'); ylabel('幅值','fontsize',16,'fontweight','bold');grid on;

y=wavread('2.wav');

%预加重

figure();subplot(211);plot(x); xlabel('样点数

','fontsize',16,'fontweight','bold');

ylabel('原始波形(幅值)','fontsize',16,'fontweight','bold'); xx=double(y);

subplot(212);plot(xx); xlabel('样点数','fontsize',16,'fontweight','bold');

ylabel('预加重波形（幅值）','fontsize',16,'fontweight','bold');

%对指定帧位置进行加窗处理 Q=y';

N=256;%窗长

Hamm=hamming(N);%加窗（汉明窗） Rect=rectwin(N);%加窗（矩形窗） frame=60;%需要处理的帧位置

M=Q(((frame-1)*(N/2)+1):((frame-1)*(N/2)+N));

Frame=M.*Hamm';%加窗后的语音帧 frame=M.*Rect';

figure();subplot(211);plot(Frame); ylabel('汉明窗

','fontsize',16,'fontweight','bold'); subplot(212);plot(frame); ylabel('矩形窗

','fontsize',16,'fontweight','bold');

%语音信号分帧

figure();subplot(211);plot(y);

xlabel('样点数','fontsize',16,'fontweight','bold');

ylabel('原始','fontsize',16,'fontweight','bold'); y=enframe(y,256,80);

subplot(212);plot(y);xlabel('帧数','fontsize',16,'fontweight','bold');

ylabel('分帧','fontsize',16,'fontweight','bold');

%端点检测

[x1,x2]=vad(x);%调用函数vad实现

%浊音， 取13270--13510个点 %短时自相关函数 temp=y(13271:13510); Rn1=zeros(1,240); for nn=1:240

for ii=1:240-nn

Rn1(nn)=Rn1(nn)+temp(ii)*temp(nn+ii); end end

figure(6);

subplot(211);jj=1:240;plot(jj,Rn1,'b');title('浊音自相关函数','fontsize',16,'fontweight','bold');

xlabel('帧数','fontsize',16,'fontweight','bold'); ylabel('短时自相关函数

精心设计的基于MATLAB的代码设计

','fontsize',16,'fontweight','bold');grid on;

%清音， 取12120--12360个点 %短时自相关函数 temp=y(12121:12360); Rn2=zeros(1,240); for nn=1:240

for ii=1:240-nn

Rn2(nn)=Rn2(nn)+temp(ii)*temp(nn+ii); end end

figure(6);

subplot(212);jj=1:240;plot(jj,Rn2,'b'); title('清音自相关函

数

','fontsize',16,'fontweight','bold');

xlabel('帧数','fontsize',16,'fontweight','bold'); ylabel('短时自相关函数','fontsize',16,'fontweight','bold');grid on;

分帧功能子程序：

function f=enframe(x,win,inc)

% F = ENFRAME(X,LEN) splits the vector X(:) up into

% frames. Each frame is of length LEN and occupies

% one row of the output matrix. The last few frames of X

% will be ignored if its length is not divisible by LEN.

% It is an error if X is shorter than LEN.

nx=length(x(:)); nwin=length(win); if (nwin == 1) len = win; else

len = nwin; end

if (nargin < 3) inc = len;

end

nf = fix((nx-len+inc)/inc); f=zeros(nf,len);

indf= inc*(0:(nf-1)).'; inds = (1:len);

f(:) = x(indf(:,ones(1,len))+inds(ones(nf,1),:)); if (nwin > 1) w = win(:)';

f = f .* w(ones(nf,1),:); End

选端点功能子程序：

function [x1,x2] = vad(x) % [x]=audioread('1.wav');

%幅度归一化到[-1,1] x = double(x);

x = x / max(abs(x));

%常数设置

FrameLen = 240; FrameInc = 80;

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);

tmp2 = enframe(x(2:end) , FrameLen, FrameInc);

signs = (tmp1.*tmp2)<0; diffs = (tmp1 -tmp2)>0.02; zcr = sum(signs.*diffs, 2);

精心设计的基于MATLAB的代码设计

%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 = 0; x2 = 0;

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 = 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; 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, break; end end

count = count-silence/2; x2 = x1 + count -1;

figure(); subplot(311) plot(x)

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

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');

line([x1 x1], [min(amp),max(amp)], 'Color', 'red');

line([x2 x2], [min(amp),max(amp)], 'Color', 'red');

subplot(313) plot(zcr);

axis([1 length(zcr) 0 max(zcr)]) ylabel('ZCR');

line([x1 x1], [min(zcr),max(zcr)], 'Color', 'red'); line([x2 x2], [min(zcr),max(zcr)], 'Color', 'red');