---------------------考试---------------------------学资学习网---------------------押题------------------------------语音信号处理实验班级：学号：姓名：实验一基于MATLAB的语音信号时域特征分析（2学时）短时能量）1．（1）加矩形窗a=wavread('mike.wav');a=a(:,1);subplot(6,1,1),plot(a);N=32;for i=2:6h=linspace(1,1,2.^(i-2)*N);%形成一个矩形窗，长度为2.^(i-2)*NEn=conv(h,a.*a);% 求短时能量函数Ensubplot(6,1,i),plot(En);if(i==2) ,legend('N=32');elseif(i==3), legend('N=64');elseif(i==4) ,legend('N=128');elseif(i==5) ,legend('N=256');elseif(i==6) ,legend('N=512');endend10-100.511.522.534x 104 20 N=3232.51.5200.514x 10 50 N=6431.50.51022.54x 10 1050 N=12831.5202.50.514x 10 20100 N=256322.50.511.504x 10 40200 N=5123100.51.522.54x 10（2）加汉明窗a=wavread('mike.wav');a=a(:,1);subplot(6,1,1),plot(a);N=32;for i=2:6h=hanning(2.^(i-2)*N);%形成一个汉明窗，长度为2.^(i-2)*NEn求短时能量函数En=conv(h,a.*a);%subplot(6,1,i),plot(En);if(i==2), legend('N=32');elseif(i==3), legend('N=64');elseif(i==4) ,legend('N=128');elseif(i==5) ,legend('N=256');elseif(i==6) ,legend('N=512');endend10-100.511.522.534x 102 10 N=3232.51.5020.514x 10 420 N=64311.522.50.504x 10 420 N=12831.5202.50.514x 10 1050 N=25631.522.500.514x 10 20100 N=512322.50.5011.54x 102）短时平均过零率a=wavread('mike.wav');a=a(:,1);n=length(a);N=320;subplot(3,1,1),plot(a);h=linspace(1,1,N);En=conv(h,a.*a); %求卷积得其短时能量函数Ensubplot(3,1,2),plot(En);for i=1:n-1if a(i)>=0b(i)= 1;elseb(i) = -1;endif a(i+1)>=0b(i+1)=1;elseb(i+1)= -1;endw(i)=abs(b(i+1)-b(i)); %求出每相邻两点符号的差值的绝对值endk=1;j=0;while (k+N-1)<nZm(k)=0;for i=0:N-1;Zm(k)=Zm(k)+w(k+i);endj=j+1;k=k+N/2; %每次移动半个窗endfor w=1:jQ(w)=Zm(160*(w-1)+1)/(2*N); %短时平均过零率endsubplot(3,1,3),plot(Q),grid;10-100.511.522.534x 102010000.511.522.534x 100.500204060801001201401601803）自相关函数N=240y=wavread('mike.wav');y=y(:,1);x=y(13271:13510);x=x.*rectwin(240);R=zeros(1,240);for k=1:240for n=1:240-kR(k)=R(k)+x(n)*x(n+k);endendj=1:240;plot(j,R);grid;2.521.510.50-0.5-1-1.5050100150200250分析语音信号频域特征MATLAB基于实验二1）短时谱cleara=wavread('mike.wav');a=a(:,1);subplot(2,1,1),plot(a);title('original signal');gridN=256;h=hamming(N);for m=1:Nb(m)=a(m)*h(m)endy=20*log(abs(fft(b)))subplot(2,1,2)plot(y);title('短时谱');gridoriginal signal10.50-0.5-100.511.522.534x 10谱时短10.5000.20.40.60.811.21.41.61.822）语谱图[x,fs,nbits]=wavread('mike.wav')x=x(:,1);specgram(x,512,fs,100);xlabel('时间(s)');ylabel('频率(Hz)'););'语谱图'title(语谱图50004000)3000zH(率频2000100000.511.52(s)时间3）倒谱和复倒谱（1）加矩形窗时的倒谱和复倒谱cleara=wavread('mike.wav',[4000,4350]);a=a(:,1);N=300;h=linspace(1,1,N);for m=1:Nb(m)=a(m)*h(m);endc=cceps(b);c=fftshift(c);d=rceps(b);d=fftshift(d);subplot(2,1,1)plot(d);title('加矩形窗时的倒谱')subplot(2,1,2)) '加矩形窗时的复倒谱'plot(c);title(加矩形窗时的倒谱10-1-2050100150200250300加矩形窗时的复倒谱1050-5-10050100150200250300（2）加汉明窗时的倒谱和复倒谱cleara=wavread('mike.wav',[4000,4350]);a=a(;,1);N=300;h=hamming(N);for m=1:Nb(m)=a(m)*h(m);endc=cceps(b);c=fftshift(c);d=rceps(b);d=fftshift(d);subplot(2,1,1)plot(d);title('加汉明窗时的倒谱')subplot(2,1,2)) '加汉明窗时的复倒谱'plot(c);title(加汉明窗时的倒谱10-1-2-3050100150200250300加汉明窗时的复倒谱1050-5-10050100150200250300实验三基于MATLAB的LPC分析MusicSource = wavread('mike.wav');MusicSource=MusicSource(:,1);Music_source = MusicSource';N = 256; % window length，N = 100 -- 1000;Hamm = hamming(N); % create Hamming windowframe = input('请键入想要处理的帧位置= ');% origin is current frameorigin = Music_source(((frame - 1) * (N / 2) + 1):((frame - 1) * (N / 2) + N));Frame = origin .* Hamm';%%Short Time Fourier Transform%[s1,f1,t1] = specgram(MusicSource,N,N/2,N);[Xs1,Ys1] = size(s1);for i = 1:Xs1FTframe1(i) = s1(i,frame);endN1 = input('请键入预测器阶数= '); % N1 is predictor's order[coef,gain] = lpc(Frame,N1); % LPC analysis using Levinson-Durbin recursionest_Frame = filter([0 -coef(2:end)],1,Frame); % estimate frame(LP)FFT_est = fft(est_Frame);err = Frame - est_Frame; % error% FFT_err = fft(err);subplot(2,1,1),plot(1:N,Frame,1:N,est_Frame,'-r');grid;title('原始语音帧vs.预测后语音帧') subplot(2,1,2),plot(err);grid;title('误差');pause%subplot(2,1,2),plot(f',20*log(abs(FTframe2)));grid;title('短时谱')%% Gain solution using G^2 = Rn(0) - sum(ai*Rn(i)),i = 1,2,...,P%fLength(1 : 2 * N) = [origin,zeros(1,N)];Xm = fft(fLength,2 * N);X = Xm .* conj(Xm);Y = fft(X , 2 * N);Rk = Y(1 : N);PART = sum(coef(2 : N1 + 1) .* Rk(1 : N1));G = sqrt(sum(Frame.^2) - PART);A = (FTframe1 - FFT_est(1 : length(f1'))) ./ FTframe1 ; % inverse filter A(Z)subplot(2,1,1),plot(f1',20*log(abs(FTframe1)),f1',(20*log(abs(1 ./ A))),'-r');grid;title('短时谱'); subplot(2,1,2),plot(f1',(20*log(abs(G ./ A))));grid;title('LPC谱');pause%plot(abs(ifft(FTframe1 ./ (G ./ A))));grid;title('excited')%plot(f1',20*log(abs(FFT_est(1 : length(f1')) .* A / G )));grid;%pause%% find_pitch%temp = FTframe1 - FFT_est(1 : length(f1'));% not move higher frequncepitch1 = log(abs(temp));pLength = length(pitch1);result1 = ifft(pitch1,N);% move higher frequncepitch1((pLength - 32) : pLength) = 0;result2 = ifft(pitch1,N);% direct do real cepstrum with errpitch = fftshift(rceps(err));origin_pitch = fftshift(rceps(Frame));subplot(211),plot(origin_pitch);grid;title('原始语音帧倒谱(直接调用函数)');subplot(212),plot(pitch);grid;title('预测误差倒谱(直接调用函数)');pausesubplot(211),plot(1:length(result1),fftshift(real(result1)));grid;title('预测误差倒谱(根据定义编写，没有去除高频分量)');subplot(212),plot(1:length(result2),fftshift(real(result2)));grid;title('预测误差倒谱(根据定义编);)'写，去除高频分量原始语音帧vs.预测后语音帧0.40.20-0.2-0.4050100150200250300差误0.20.10-0.1-0.2300250100050150200短时谱500-50-100010203040506070谱LPC100806040010203040506070原始语音帧倒谱(直接调用函数)0.50-0.5-1050100150200250300预测误差倒谱(直接调用函数)0.50-0.5-1050100150200250300预测误差倒谱(根据定义编写，没有去除高频分量)0.20-0.2-0.4-0.6050100150200250300预测误差倒谱(根据定义编写，去除高频分量)0.10-0.1-0.2-0.3050100150200250300预测误差倒谱(根据定义编写，没有去除高频分量)0.20-0.2-0.4-0.6050100150200250300预测误差倒谱(根据定义编写，去除高频分量)0.10-0.1-0.2-0.3050100150200250300预测误差倒谱(根据定义编写，没有去除高频分量)0.20-0.2-0.4-0.6050100150200250300预测误差倒谱(根据定义编写，去除高频分量)0.10-0.1-0.2-0.3050100150200250300实验四基于VQ的特定人孤立词语音识别研究1、mfcc.mccc = mfcc(x)function);'m'bank=melbankm(24,256,8000,0,0.5,bank=full(bank); bank=bank/max(bank(:));k=1:12for n=0:23; dctcoef(k,:)=cos((2*n+1)*k*pi/(2*24));endw = 1 + 6 * sin(pi * [1:12] ./ 12);w = w/max(w);xx=double(x);xx=filter([1 -0.9375],1,xx);xx=enframe(xx,256,80); i=1:size(xx,1)for y = xx(i,:); s = y' .*hamming(256); t = abs(fft(s)); t = t.^2; c1=dctcoef * log(bank * t(1:129));c2 = c1.*w'; m(i,:)=c2';enddtm = zeros(size(m)); i=3:size(m,1)-2for dtm(i,:) = -2*m(i-2,:) - m(i-1,:) + m(i+1,:) + 2*m(i+2,:);end dtm = dtm / 3;ccc = [m dtm];ccc = ccc(3:size(m,1)-2,:);2、vad.m[x1,x2] = vad(x)function x = double(x);x = x / max(abs(x));FrameLen = 240;FrameInc = 80;amp1 = 10;amp2 = 2;zcr1 = 10;zcr2 = 5;% 6*10ms = 30ms maxsilence = 8;% 15*10ms = 150ms minlen = 15;status = 0;count = 0;silence = 0;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);amp = sum(abs(enframe(filter([1 -0.9375], 1, x), FrameLen, FrameInc)),2);amp1 = min(amp1, max(amp)/4);amp2 = min(amp2, max(amp)/8);x1 = 0;x2 = 0; n=1:length(zcr)for goto = 0; status switch{0,1} caseif amp(n) > amp1x1 = max(n-count-1,1); status = 2; silence = 0; count = count + 1;... amp(n) > amp2 | elseif zcr(n) > zcr2status = 1; count = count + 1;else status = 0; count = 0;end2, caseamp(n) > amp2 | ...if zcr(n) > zcr2 count = count + 1; elsesilence = silence+1; if silence < maxsilencecount = count + 1; count < minlen elseifstatus = 0; silence = 0; count = 0;elsestatus = 3;endend3, case; break endcount = count-silence/2;x2 = x1 + count -1;3、codebook.m%clear; xchushi= codebook(m)function[a,b]=size(m);[m1,m2]=szhixin(m); [m3,m4]=szhixin(m2);[m1,m2]=szhixin(m1);[m7,m8]=szhixin(m4);[m5,m6]=szhixin(m3);[m3,m4]=szhixin(m2);[m1,m2]=szhixin(m1);[m15,m16]=szhixin(m8);[m13,m14]=szhixin(m7);[m11,m12]=szhixin(m6);[m9,m10]=szhixin(m5);[m7,m8]=szhixin(m4);[m5,m6]=szhixin(m3);[m3,m4]=szhixin(m2);[m1,m2]=szhixin(m1);chushi(1,:)=zhixinf(m1);chushi(2,:)=zhixinf(m2);chushi(3,:)=zhixinf(m3);chushi(4,:)=zhixinf(m4); chushi(5,:)=zhixinf(m5);chushi(6,:)=zhixinf(m6);chushi(7,:)=zhixinf(m7); chushi(8,:)=zhixinf(m8);chushi(9,:)=zhixinf(m9);chushi(10,:)=zhixinf(m10); chushi(11,:)=zhixinf(m11);chushi(12,:)=zhixinf(m12);chushi(13,:)=zhixinf(m13);chushi(14,:)=zhixinf(m14);chushi(15,:)=zhixinf(m15);chushi(16,:)=zhixinf(m16);sumd=zeros(1,1000);k=1;dela=1;xchushi=chushi;(k<=1000)while sum=ones(1,16); p=1:a fori=1:16 for d(i)=odistan(m(p,:),chushi(i,:));enddmin=min(d); sumd(k)=sumd(k)+dmin;i=1:16ford(i)==dmin if xchushi(i,:)=xchushi(i,:)+m(p,:); sum(i)=sum(i)+1;end endendi=1:16forxchushi(i,:)=xchushi(i,:)/sum(i);endk>1if dela=abs(sumd(k)-sumd(k-1))/sumd(k);end k=k+1; chushi=xchushi; end return4、testvq.mclear;)这是一个简易语音识别系统，请保证已经将您的语音保存在相应文件夹中'disp(')正在训练您的语音模版指令，请稍后...'disp(' i=1:10for,i-1);\\ú.wav'海儿的声音 fname =sprintf('D:\\matlab\\work\\dtw1\\ x = wavread(fname); [x1 x2] = vad(x); m = mfcc(x); m = m(x1:x2-5,:);ref(i).code=codebook(m);end)?''语音指令训练成功，恭喜！disp()...''正在测试您的测试语音指令，请稍后disp( i=1:10for,i-1);海儿的声音\\?.wav'fname = sprintf('D:\\matlab\\work\\dtw1\\ x = wavread(fname);[x1 x2] = vad(x); mn = mfcc(x); mn = mn(x1:x2-5,:);%mn = mn(x1:x2,:) test(i).mfcc = mn;end sumsumdmax=0;sumsumdmin=0;)''对训练过的语音进行测试disp( w=1:10for sumd=zeros(1,10); [a,b]=size(test(w).mfcc);i=1:10forp=1:a for j=1:16 ford(j)=odistan(test(w).mfcc(p,:),ref(i).code(j,:));dmin=min(d);%×üê§?? sumd(i)=sumd(i)+dmin;end end sumdmin=min(sumd)/a;sumdmin1=min(sumd);sumdmax(w)=max(sumd)/a; sumsumdmin=sumdmin+sumsumdmax;sumsumdmax=sumdmax(w)+sumsumdmax;)正在匹配您的语音指令，请稍后...'disp(' i=1:10for (sumd(i)==sumdmin1) if (i) switch 1 case);前'', '您输入的语音指令为:%s; 识别结果为%s\n','前fprintf(' 2 case);', ''后:%s; 识别结果为%s\n','后 fprintf('您输入的语音指令为 3case);', '左识别结果为%s\n','左' fprintf('您输入的语音指令为:%s;4case);''右,'右', 您输入的语音指令为 fprintf('a:%s; 识别结果为%s\n' 5case);''东'东', fprintf('您输入的语音指令为:%s; 识别结果为%s\n', 6case);南'南', ' fprintf('您输入的语音指令为:%s; 识别结果为%s\n',' 7 case);', '西,:%s; 识别结果为%s\n''西' fprintf('您输入的语音指令为 8case);''北,'北', 您输入的语音指令为 fprintf(':%s; 识别结果为%s\n' 9case);上'', ', fprintf('您输入的语音指令为a:%s; 识别结果为%s\n''上 10case);下', '下'',您输入的语音指令为 fprintf('a:%s; 识别结果为%s\n'otherwise); 'error' fprintf(endendend end delamin=sumsumdmin/10;delamax=sumsumdmax/10;)''对没有训练过的语音进行测试disp()正在测试你的语音，请稍后...'disp(' i=1:10for,i-1);fname =sprintf('D:\\matlab\\work\\dtw1\\o￡?ùμ?éùò?\\?.wav' x = wavread(fname);[x1 x2] = vad(x); mn = mfcc(x); mn = mn(x1:x2-5,:);%mn = mn(x1:x2,:)test(i).mfcc = mn;endw=1:10for sumd=zeros(1,10); [a,b]=size(test(w).mfcc); i=1:10forp=1:a for j=1:16ford(j)=odistan(test(w).mfcc(p,:),ref(i).code(j,:));enddmin=min(d);%×üê§?? sumd(i)=sumd(i)+dmin;end end sumdmin=min(sumd);z=0; i=1:10for (((sumd(i))/a)>delamax)|| if z=z+1;endend)...'disp('正在匹配您的语音指令，请稍后z<=3if i=1:10for (sumd(i)==sumdmin) if (i)switch1case);'前', '前',%s\n'识别结果为:%s; 您输入的语音指令为' fprintf(2 case);'后', ':%s; 识别结果为%s\n','后 fprintf('您输入的语音指令为3case);', '左识别结果为%s\n','左' fprintf('您输入的语音指令为:%s;4case);''右,'右', 识别结果为 fprintf('您输入的语音指令为a:%s; %s\n' 5case);''东'东', fprintf('您输入的语音指令为:%s; 识别结果为%s\n', 6 case);南'南', ' fprintf('您输入的语音指令为:%s; 识别结果为%s\n',' 7 case);', '西西:%s; 识别结果为%s\n','' fprintf('您输入的语音指令为 8case );''北,'北', 识别结果为 fprintf('您输入的语音指令为:%s; %s\n' 9case);上'', '上 fprintf('您输入的语音指令为a:%s; 识别结果为%s\n',' 10case);下'','下', 识别结果为 fprintf('您输入的语音指令为a:%s; %s\n'otherwise ); fprintf('error'endendend else)您输入的语音无效?￡?\n'' fprintf(end end。
