Voice synthesis on ISR

Intéressé pour voir la source ? Si vous utilisez MATLAB, pas de problème...

The data frame looks like this:

    dw 67,110,30,28,26,35,45,31 
    db 0x81,0x81,0x81,0x91,0x91,0x92,0x92,0x92 
    dw 31,30,621,143,47,62,67,373 
    db 0x81,0x91,0x91,0x92,0x92,0xA2,0xB3,0xE9 

There are 8 frequencies (actually periods) and 8 volumes (the lower nibbles is coded for SCC, the upper for PSG)
In this way the same data are used in both cases, with and without an SCC detected
The tones are sorted by relevance, so when the PSG is alone, it will use the last 3 tones.

The real problem is how to generate the data from a speech sample.
My matlab script basically does this

- read a wav file
- low pass filter the input in 500Hz-6000Hz
- segment the audio file in chunks of 1/60 of sec
- compute the power spectrum of the chunk (via FFT)
- find the 8 biggest local maxima of the power spectrum making sure they do not mask each other
- encode their frequencies and amplitudes as msx periods and volumes

Simple but with some manual tweaking on the encoding side

No idea, this is the main script, it compiles too.
Just replace the path where wav files are with your own path.
Someone with octave could tell if it works.

close all;
clear;
path = 'wav\SKYJAGUAR\';


names = dir([path '*.wav']);
nfiles = size(names,1);

for ii = 1:nfiles 
    ii
    name = [ path names(ii).name];

    [Y,FS,NBITS] = wavread(name);
    if size(Y,2)>1
     X = Y(:,1)+Y(:,2);
    else
     X = Y;
    end

    Wn = [450/FS, 6000/FS];
    
    [Bbp,Abp]=butter(5,Wn); 

    Tntsc = 1/60;

    Nntsc = fix(Tntsc*FS);

    Nblk = fix(length(X)/Nntsc);
    X = X(1:Nblk*Nntsc);
    L = length(X);

    t = [1:Nntsc]';

    Y = zeros(Nblk*Nntsc,1);
    f = zeros(Nblk,8);
    a = zeros(Nblk,8);
    p = zeros(1,8);
    
    X = filter(Bbp,Abp,X);
    
    for i=1:Nblk
        x = X((i-1)*Nntsc+1:i*Nntsc);

        XF = abs(fft(x));
        [pks,locs]= findpeaks(XF(1:round(Nntsc/2)),'SORTSTR','descend'); 

        if size(pks,1)<8
            y = zeros(1,8);
            y(1:length(pks)) = pks;
            pks = y;
            y = round(Nntsc/2)-7:round(Nntsc/2);
            y(1:length(locs)) = locs;
            locs = y;
        end
        
         pks = pks(8:-1:1);
         locs = locs(8:-1:1);
        
        y = zeros(size(x));
        freq = zeros(1,8);
        amp  = zeros(1,8);
        
        for  ti=1:8
            j = locs(ti);   
            freq(ti) = (j-1)/Nntsc*FS;
            amp(ti) = abs(XF(j))/Nntsc;
            y = y + amp(ti)*(sin(2*pi*freq(ti)*t/FS+p(ti)));
            p(ti) = 2*pi*freq(ti)*t(end)/FS;
        end

        Y((i-1)*Nntsc+1:i*Nntsc) =  y;
        f(i,:) = freq;
        a(i,:) = amp;
    end

%    sound(X,FS)
%    sound(Y,FS)

    TP = uint16(3579545./(32*f));

    m = max(a(:));
    nscc = uint8(a/m*15);

    npsg = 2*log2(a/m)+15;
    npsg(isinf(npsg))=0;
    npsg = uint8(ceil(npsg));

    n = npsg*16+nscc;		% in the same byte psg and scc volumes
	
    fid = fopen([name 'frm_scc3.txt'],'w');
    for i = 1:Nblk
        fprintf(fid,'    dw %d,%d,%d,%d,%d,%d,%d,%d \n',TP(i,1),TP(i,2),TP(i,3),TP(i,4),TP(i,5),TP(i,6),TP(i,7),TP(i,8));
        fprintf(fid,'    db 0x%s,0x%s,0x%s,0x%s,0x%s,0x%s,0x%s,0x%s \n',dec2hex(n(i,1),2),dec2hex(n(i,2),2),dec2hex(n(i,3),2),dec2hex(n(i,4),2),dec2hex(n(i,5),2),dec2hex(n(i,6),2),dec2hex(n(i,7),2),dec2hex(n(i,8),2));
    end
    fclose(fid);

end

fid = fopen('frm_scc3.txt','w');
fprintf(fid,'nfiles: equ  %d \n\n',nfiles);

fprintf(fid,'   page 0\n');

fprintf(fid,'frames: \n');


for ii = 1:nfiles
    fprintf(fid,'   dw frame%d\n',ii-1);
    fprintf(fid,'   db :frame%d\n',ii-1);
end

for ii = 1:nfiles 
    fprintf(fid,'   page 1..31\n');
    name = [ path names(ii).name];
    fprintf(fid,'frame%d: \n',ii-1);
    fprintf(fid,'   include %s \n',[name 'frm_scc3.txt']);
    fprintf(fid,'   db	080h\n');
end
fclose(fid);

!sjasm -Iasm -s sccLOFI3.asm

Totally true! This is why I was asking for snippets to detect OPLL and play tones at variable volumes and frequencies. OPLL is still a obscure for me, but it should be perfectly suitable for the purpose.