untitled.m

MFCC参数计算

ccc = MFCC(x,Fs,nM,nC,nfft,fl,fh,ovlp)

%        This is to calculate MFCC coefficients of input data 'x'. Default dimension 
% of MFCC is 24, including mfcc and △mfcc.
%
% Input Parameters:
% x:    input data, must be a vector.
% Fs:   sample frequency
% nM:   dimension of MFCC coefficients
% nC:   number of filters
% nfft: number of fft and it is also the length of a of data
% fl:   the lowest frequency =  fl * Fs
% fh:   the highest frequency = fh * Fs, so fh <= 0.5
% ovlp: overlap, default 0.5
%
% Output Parameter:
% ccc: MFCC matrix, each row is a MFCC pattern
%
%   xiupingping@smth provided a matlab program to generate MFCC
% patterns. This program derived from it.
%   No copyright reversed 
%                                                   QingRen
%                                                   qingren_ny#126.com

if nargin < 2    Fs = 8000;    end
if nargin < 3   nM = 12;    end
if nargin < 4    nC = 24;    end
if nargin < 5    nfft = 256;    end
if nargin < 6    fl = 0;    end
if nargin < 7    fh = 0.5;    end
if nargin < 8    ovlp = 0.5;    end


x = x(:);

% ----- mel filter bank -----
% melbankm.m ect, you can get them from toolbox "VoiceBox"
% http://www.ee.ic.ac.uk/hp/staff/dmb/voicebox/voicebox.html

bank = melbankm(nC,nfft,Fs,fl,fh);
bank = full(bank);
bank = bank / max(bank(:));
 

%  ----- DCT coefficients, a (N×nC) matrix -----
% Reference 
% [1] "Generalized Mel frequency cepstral coefficients for large-vocabulary
%        speeker-independent continuous-speech recognition"  IEEE 1996
% [2] "Comparison of parametric representations for monosyllabic word 
% recognition" IEEE Trans Acoust.Speech.Signal Processing 1980

j = 0:nC-1;
for k = 1:nM
    dctcoef(k,:) = cos(k * (j+0.5) * pi / nC); 
end
 
% Ceplifter
% Reference:   HTK book v3.1
w = 1 + (nM/2) * sin(pi*[1:nM]./nM);
w = w / max(w);
 
% pre-emphasis filtering
% x = double(x);
% x = filter([1 -0.95],1,x);


% ----- Calculate MFCC coefficients of each -----
L_x = length(x);
frm_move = floor(nfft * (1 - ovlp));
i = 0; 

while ((i*frm_move+nfft) <= L_x)
    in = x(i*frm_move+1:i*frm_move+nfft);
    in = in ./ max(abs(in));
    in = in .* hamming(nfft);
    
    % --- Calculate the energy spectrum ---
    s = abs(fft(in));  
    t = s.^2;
    t = t + 2*realmin;
    t = t(1:nfft/2+1);
    
    % --- Calculate the energy in each channel ---
    t1 = bank * t;
    
    % --- Calculate MFCC ---
    t1 = log10(t1);
    c1 = dctcoef * t1;
    c2 = c1.*w';
    m(i+1,:) = c2';
    
    i = i + 1;
end

ccc = m;

% get △mfcc
% 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;
 
% combine mfcc and △mfcc
% ccc = [m dtm];
% ccc=ccc(3:size(m,1)-2,:);