// static
void SdSoundCaptureAL::Update()
{
ALint iSamplesAvailable;
// Find out how many samples have been captured
alcGetIntegerv(pCaptureDevice, ALC_CAPTURE_SAMPLES, 1, &iSamplesAvailable);
// When we have enough data to fill our BUFFERSIZE byte buffer, grab the samples
if (iSamplesAvailable > (FFTBufferSize / sWaveHeader.wfex.nBlockAlign))
{
BtU32 numSamples = FFTBufferSize / sWaveHeader.wfex.nBlockAlign;
// Consume Samples
alcCaptureSamples(pCaptureDevice, inWAV, numSamples );
ALCshort *buffer = (ALCshort*)inWAV;
// Get the average volume
BtU32 averageVolume = 0;
for( BtU32 i=0; i<numSamples; i++ )
{
BtS32 val = buffer[i];
averageVolume += MtAbs( val );
}
volume = ((BtFloat)averageVolume) / numSamples;
SamplesRead = numSamples;
// Calculate the pitch
m_pitch = find_pitch( (BtU8*)buffer, MIN_FREQ, MAX_FREQ );
// Write this to a file
if( audioFile )
{
// Write the audio data to a file
fwrite(inWAV, FFTBufferSize, 1, audioFile );
}
// Record total amount of data recorded
iDataSize += FFTBufferSize;
}
}
void melp_ana(float sp_in[],struct melp_param *par)
{
int i;
int begin;
float sub_pitch;
float temp,pcorr,bpthresh;
float r[LPC_ORD+1],refc[LPC_ORD+1],lpc[LPC_ORD+1];
float weights[LPC_ORD];
/* Remove DC from input speech */
dc_rmv(sp_in,&speech[IN_BEG],dcdel,FRAME);
/* Copy input speech to pitch window and lowpass filter */
v_equ(&sigbuf[LPF_ORD],&speech[PITCH_BEG],PITCH_FR);
v_equ(sigbuf,lpfsp_del,LPF_ORD);
polflt(&sigbuf[LPF_ORD],lpf_den,&sigbuf[LPF_ORD],LPF_ORD,PITCH_FR);
v_equ(lpfsp_del,&sigbuf[FRAME],LPF_ORD);
zerflt(&sigbuf[LPF_ORD],lpf_num,&sigbuf[LPF_ORD],LPF_ORD,PITCH_FR);
/* Perform global pitch search at frame end on lowpass speech signal */
/* Note: avoid short pitches due to formant tracking */
fpitch[END] = find_pitch(&sigbuf[LPF_ORD+(PITCH_FR/2)],&temp,
(2*PITCHMIN),PITCHMAX,PITCHMAX);
/* Perform bandpass voicing analysis for end of frame */
bpvc_ana(&speech[FRAME_END], fpitch, &par->bpvc[0], &sub_pitch);
/* Force jitter if lowest band voicing strength is weak */
if (par->bpvc[0] < VJIT)
par->jitter = MAX_JITTER;
else
par->jitter = 0.0;
/* Calculate LPC for end of frame */
window(&speech[(FRAME_END-(LPC_FRAME/2))],win_cof,sigbuf,LPC_FRAME);
autocorr(sigbuf,r,LPC_ORD,LPC_FRAME);
lpc[0] = 1.0;
lpc_schur(r,lpc,refc,LPC_ORD);
lpc_bw_expand(lpc,lpc,BWFACT,LPC_ORD);
/* Calculate LPC residual */
zerflt(&speech[PITCH_BEG],lpc,&sigbuf[LPF_ORD],LPC_ORD,PITCH_FR);
/* Check peakiness of residual signal */
begin = (LPF_ORD+(PITCHMAX/2));
temp = peakiness(&sigbuf[begin],PITCHMAX);
/* Peakiness: force lowest band to be voiced */
if (temp > PEAK_THRESH) {
par->bpvc[0] = 1.0;
}
/* Extreme peakiness: force second and third bands to be voiced */
if (temp > PEAK_THR2) {
par->bpvc[1] = 1.0;
par->bpvc[2] = 1.0;
}
/* Calculate overall frame pitch using lowpass filtered residual */
par->pitch = pitch_ana(&speech[FRAME_END], &sigbuf[LPF_ORD+PITCHMAX],
sub_pitch,pitch_avg,&pcorr);
bpthresh = BPTHRESH;
/* Calculate gain of input speech for each gain subframe */
for (i = 0; i < NUM_GAINFR; i++) {
if (par->bpvc[0] > bpthresh) {
/* voiced mode: pitch synchronous window length */
temp = sub_pitch;
par->gain[i] = gain_ana(&speech[FRAME_BEG+(i+1)*GAINFR],
temp,MIN_GAINFR,2*PITCHMAX);
}
else {
temp = 1.33*GAINFR - 0.5;
par->gain[i] = gain_ana(&speech[FRAME_BEG+(i+1)*GAINFR],
temp,0,2*PITCHMAX);
}
}
/* Update average pitch value */
if (par->gain[NUM_GAINFR-1] > SILENCE_DB)
temp = pcorr;
else
temp = 0.0;
pitch_avg = p_avg_update(par->pitch, temp, VMIN);
/* Calculate Line Spectral Frequencies */
lpc_pred2lsp(lpc,par->lsf,LPC_ORD);
/* Force minimum LSF bandwidth (separation) */
lpc_clamp(par->lsf,BWMIN,LPC_ORD);
/* Quantize MELP parameters to 2400 bps and generate bitstream */
/* Quantize LSF's with MSVQ */
vq_lspw(weights, &par->lsf[1], lpc, LPC_ORD);
msvq_enc(&par->lsf[1], weights, &par->lsf[1], vq_par);
par->msvq_index = vq_par.indices;
/* Force minimum LSF bandwidth (separation) */
lpc_clamp(par->lsf,BWMIN,LPC_ORD);
/* Quantize logarithmic pitch period */
/* Reserve all zero code for completely unvoiced */
par->pitch = log10(par->pitch);
quant_u(&par->pitch,&par->pitch_index,PIT_QLO,PIT_QUP,PIT_QLEV);
par->pitch = pow(10.0,par->pitch);
/* Quantize gain terms with uniform log quantizer */
q_gain(par->gain, par->gain_index,GN_QLO,GN_QUP,GN_QLEV);
/* Quantize jitter and bandpass voicing */
quant_u(&par->jitter,&par->jit_index,0.0,MAX_JITTER,2);
par->uv_flag = q_bpvc(&par->bpvc[0],&par->bpvc_index,bpthresh,
NUM_BANDS);
/* Calculate Fourier coefficients of residual signal from quantized LPC */
fill(par->fs_mag,1.0,NUM_HARM);
if (par->bpvc[0] > bpthresh) {
lpc_lsp2pred(par->lsf,lpc,LPC_ORD);
zerflt(&speech[(FRAME_END-(LPC_FRAME/2))],lpc,sigbuf,
LPC_ORD,LPC_FRAME);
window(sigbuf,win_cof,sigbuf,LPC_FRAME);
find_harm(sigbuf, par->fs_mag, par->pitch, NUM_HARM, LPC_FRAME);
}
/* quantize Fourier coefficients */
/* pre-weight vector, then use Euclidean distance */
window(&par->fs_mag[0],w_fs,&par->fs_mag[0],NUM_HARM);
fsvq_enc(&par->fs_mag[0], &par->fs_mag[0], fs_vq_par);
/* Set MELP indeces to point to same array */
par->fsvq_index = fs_vq_par.indices;
/* Update MSVQ information */
par->msvq_stages = vq_par.num_stages;
par->msvq_bits = vq_par.num_bits;
/* Write channel bitstream */
melp_chn_write(par);
/* Update delay buffers for next frame */
v_equ(&speech[0],&speech[FRAME],IN_BEG);
fpitch[BEGIN] = fpitch[END];
}
