melcepst.m

voice recognition feature

function c=melcepst(s,fs,w,nc,p,n,inc,fl,fh)


if nargin<2 fs=11025; end
if nargin<3 w='M'; end
if nargin<4 nc=12; end
if nargin<5 p=floor(3*log(fs)); end
if nargin<6 n=pow2(floor(log2(0.03*fs))); end
if nargin<9
   fh=0.5;   
   if nargin<8
     fl=0;
     if nargin<7
        inc=floor(n/2);
     end
  end
end

if length(w)==0
   w='M';
end

   z=enframe(s,hamming(n),inc);
%end
f=rfft(z.');
[m,a,b]=melbankm(p,n,fs,fl,fh,w);
plot(melbankm(p,n,fs)')
title('Mel Spaced Filter Bank')
axis xy
xlabel('FFT Bin');
ylabel('Amplitude')
pw=f(a:b,:).*conj(f(a:b,:));
pth=max(pw(:))*1E-20;
if any(w=='p')
   y=log(max(m*pw,pth));
else
   ath=sqrt(pth);
   y=log(max(m*abs(f(a:b,:)),ath));
end
c=rdct(y).';
nf=size(c,1);
nc=nc+1;
if p>nc
   c(:,nc+1:end)=[];
elseif p<nc
   c=[c zeros(nf,nc-p)];
end
if ~any(w=='0')
   c(:,1)=[];
   nc=nc-1;
end
if any(w=='e')
   c=[log(sum(pw)).' c];
   nc=nc+1;
end

% calculate derivative

if any(w=='D')
  vf=(4:-1:-4)/60;
  af=(1:-1:-1)/2;
  ww=ones(5,1);
  cx=[c(ww,:); c; c(nf*ww,:)];
  vx=reshape(filter(vf,1,cx(:)),nf+4,nc);
  vx(1:8,:)=[];
  ax=reshape(filter(af,1,vx(:)),nf+2,nc);
  ax(1:2,:)=[];
  vx([1 nf+2],:)=[];
  if any(w=='d')
     c=[c vx ax];
  else
     c=[c ax];
  end
elseif any(w=='d')
  vf=(4:-1:-4)/60;
  ww=ones(4,1);
  cx=[c(ww,:); c; c(nf*ww,:)];
  vx=reshape(filter(vf,1,cx(:)),nf+8,nc);
  vx(1:8,:)=[];
  c=[c vx];
end
 
if nargout<1
   [nf,nc]=size(c);
   t=((0:nf-1)*inc+(n-1)/2)/fs;
   ci=(1:nc)-any(w=='0')-any(w=='e');
   imh = imagesc(t,ci,c.');
   axis('xy');
   xlabel('Time (s)');
   ylabel('Mel-cepstrum coefficient');
	map = (0:63)'/63;
	colormap([map map map]);
	colorbar;
end