mfcc.zip_MFCC

function [ ccc ] = mfcc( x ) %MFCC 此处显示有关此函数的摘要 % mfcc完整参数形成 % 此处显示详细说明 %读取语音信号 audio = audioread(x); %归一化mel滤波器 三角滤波器 掩蔽效应 bank = melbankm(24,256,8000,0,0.5,'m'); %MELBANKM determine matrix for a mel-spaced filterbank [X,MN,MX]=(P,N,FS,FL,FH,W) % % Inputs: p number of filters in filterbank % n length of fft % fs sample rate in Hz % fl low end of the lowest filter as a fraction of fs (default = 0) % fh high end of highest filter as a fraction of fs (default = 0.5) % w any sensible combination of the following: % 't' triangular shaped filters in mel domain (default) % 'n' hanning shaped filters in mel domain % 'm' hamming shaped filters in mel domain % % 'z' highest and lowest filters taper down to zero (default) % 'y' lowest filter remains at 1 down to 0 frequency and % highest filter remains at 1 up to nyquist freqency % % If 'ty' or 'ny' is specified, the total power in the fft is preserved. % bank = full(bank);%转换为满矩阵 bank = bank/max(bank(:)); %DCT系数，一般为12&24 %12行数，24列数，从n开始内循环到外循环 for k=1:12 n=0:23; dctcoef(k,:) = cos((2*n+1)*k*pi/(2*24)); end %归一化倒谱提升窗口 w = 1 + 6*sin(pi*[1:12]./12);%有公式代入 w = w/max(w); %预加重滤波器 xx = filter([1 -0.9375],1,audio); %语音信号分帧 frame = enframe(xx,256,80); %计算每帧MFCC参数 for i = 1:size(frame,1) y = frame(i,:); s = y'.*hamming(256);%汉明窗 t = abs(fft(s));%快速傅里叶转换 t = t.^2; c1 = dctcoef*log(bank*t(1:129));%129是bank的列数 c2 = c1.*w'; m(i,:)=c2'; end %差分参数 dtm = zeros(size(m)); for i = 3:size(m,1)-2 dtm(i,:) = -2*m(i-2,:) - m(i-1,:) + m(i+1,:) + 2*m(i+2,:); end dtm = dtm/3; %合并MFCC参数 ccc = [m dtm]; %去除首尾帧 ccc = ccc(3:size(m,1)-2,:);%出现24维数是因为12阶MFCC进行一阶差分，形成24维 end