86 lines
2.5 KiB
Markdown
86 lines
2.5 KiB
Markdown
|
# Speech Synthesis
|
||
|
|
|
||
|
|
TODO
|
||
|
|
|
||
|
|
## Example
|
||
|
|
|
||
|
|
This is a simple [C](c.md) program (using [float](float.md) for simplicity of demonstration) that creates basic vowel sounds using formant synthesis (run e.g. as `gcc -lm program.c && ./a.out | aplay`, 8000 Hz 8 bit audio is supposed):
|
||
|
|
|
||
|
|
```
|
||
|
|
#include <stdio.h>
|
||
|
|
#include <math.h>
|
||
|
|
|
||
|
|
double vowelParams[] = { // vocal tract shapes, can be found in literature
|
||
|
|
// formant1 formant2 width1 width2 amplitude1 amplitude2
|
||
|
|
850, 1650, 500, 500, 1, 0.2, // a
|
||
|
|
390, 2300, 500, 450, 1, 0.9, // e
|
||
|
|
240, 2500, 300, 500, 1, 0.5, // i
|
||
|
|
250, 600, 500, 400, 1, 0.9, // o
|
||
|
|
300, 400, 400, 400, 1, 1.0 // u
|
||
|
|
};
|
||
|
|
|
||
|
|
double tone(double t, double f) // tone of given frequency
|
||
|
|
{
|
||
|
|
return sin(f * t * 2 * M_PI);
|
||
|
|
}
|
||
|
|
|
||
|
|
/* simple linear ("triangle") function for modelling spectral shape
|
||
|
|
of one formant with given frequency location, width and amplitude */
|
||
|
|
double formant(double freq, double f, double w, double a)
|
||
|
|
{
|
||
|
|
double r = ((freq - f + w / 2) * 2 * a) / w;
|
||
|
|
|
||
|
|
if (freq > f)
|
||
|
|
r = -1 * (r - a) + a;
|
||
|
|
|
||
|
|
return r > 1 ? 1 : (r < 0 ? 0 : r);
|
||
|
|
}
|
||
|
|
|
||
|
|
/* gives one sample of speech, takes two formants as input, fundamental
|
||
|
|
frequency and possible offset of both formants (can model "bigger/smaller
|
||
|
|
head") */
|
||
|
|
double speech(double t, double fundamental, double offset,
|
||
|
|
double f1, double f2,
|
||
|
|
double w1, double w2,
|
||
|
|
double a1, double a2)
|
||
|
|
{
|
||
|
|
int harmonic = 1; // number of harmonic frequency
|
||
|
|
|
||
|
|
double r = 0;
|
||
|
|
|
||
|
|
/* now generate harmonics (multiples of fundamental frequency) as the source,
|
||
|
|
and multiply them by the envelope given by formants (no need to deal with
|
||
|
|
multiplication of spectra; as we're constructing the result from basic
|
||
|
|
frequencies, we can simply multiply each by one directly): */
|
||
|
|
while (1)
|
||
|
|
{
|
||
|
|
double f = harmonic * fundamental;
|
||
|
|
double formant1 = formant(f,f1 + offset,w1,a1);
|
||
|
|
double formant2 = formant(f,f2 + offset,w2,a2);
|
||
|
|
|
||
|
|
// envelope = max(formant1,formant2)
|
||
|
|
r += (formant1 > formant2 ? formant1 : formant2) * 0.1 * tone(t,f);
|
||
|
|
|
||
|
|
if (f > 10000) // stop generating harmonics above 10000 Hz
|
||
|
|
break;
|
||
|
|
|
||
|
|
harmonic++;
|
||
|
|
}
|
||
|
|
|
||
|
|
return r > 1.0 ? 1.0 : (r < 0 ? 0 : r); // clamp between 0 and 1
|
||
|
|
}
|
||
|
|
|
||
|
|
int main(void)
|
||
|
|
{
|
||
|
|
for (int i = 0; i < 50000; ++i)
|
||
|
|
{
|
||
|
|
double t = ((double) i) / 8000.0;
|
||
|
|
double *vowel = vowelParams + ((i / 4000) % 5) * 6; // change vowels
|
||
|
|
|
||
|
|
putchar(128 + 127 *
|
||
|
|
speech(t,150,-100,vowel[0],vowel[1],vowel[2],vowel[3],vowel[4],vowel[5]));
|
||
|
|
}
|
||
|
|
|
||
|
|
return 0;
|
||
|
|
}
|
||
|
|
```
|