// Information on the quantity of data available for each client
// Outputs a list with the selected files for a defined quantity of data
int ExtractTargetDataInfo(Config& config)
{
String inputClientListFileName = config.getParam("targetIdList");
bool fixedLabelSelectedFrame;
String labelSelectedFrames;
if (config.existsParam("useIdForSelectedFrame")) // the ID of each speaker is used as labelSelectedFrame
fixedLabelSelectedFrame=false;
else{ // the label is decided by the command line and is unique for the run
labelSelectedFrames=config.getParam("labelSelectedFrames");
if (verbose) cout << "Computing on" << labelSelectedFrames << " label" << endl;
fixedLabelSelectedFrame=true;
}
unsigned long maxFrame=config.getParam("maxFrame").toLong();
String outputFilename=config.getParam("outputFilename");
ofstream outputFile(outputFilename.c_str(),ios::out| ios::trunc);
try{
XList inputClientList(inputClientListFileName,config); // read the Id + filenames for each client
XLine * linep;
if (verbose) cout << "InfoTarget" << endl;
// *********** Target loop *****************
while ((linep=inputClientList.getLine()) != NULL){ // linep gives the XLine with the Id of a given client and the list of files
String *id=linep->getElement(); // Get the Client ID (id)
outputFile<<*id;
String currentFile="";
XLine featureFileListp=linep->getElements(); // Get the list of feature file for the client (end of the line)
if (verbose) cout << "Info model ["<<*id<<"]"<<endl;
if (!fixedLabelSelectedFrame){ // the ID is used as label for selecting the frame
labelSelectedFrames=*id;
if (debug) cout <<*id<<" is used for label selected frames"<<endl;
}
// label files reading - It creates, for each file and each label, a cluster of segments - will be integrated witth the featre s - asap
SegServer segmentsServer; // Reading the segmentation files for each feature input file
LabelServer labelServer;
initializeClusters(featureFileListp,segmentsServer,labelServer,config); // Reading the segmentation files for each feature input file
unsigned long codeSelectedFrame=labelServer.getLabelIndexByString(labelSelectedFrames); // Get the index of the cluster with in interest audio segments
SegCluster& selectedSegments=segmentsServer.getCluster(codeSelectedFrame); // Gives the cluster of the selected/used segments
Seg *seg; // Will give the current segment
unsigned long frameCount=0;
selectedSegments.rewind(); // at the begin of the selected segments list
while(((seg=selectedSegments.getSeg())!=NULL) && (frameCount<maxFrame)){ // For each of the selected segments until the amount of data is get
frameCount+=seg->length();
cout << seg->sourceName()<<" "<<seg->begin()<<" "<<seg->length()<<" Total time="<<frameCount<<endl;
if (seg->sourceName()!=currentFile){
outputFile<<" "<<seg->sourceName();
currentFile=seg->sourceName();
}
} // end of the initial Train Iteration loop
outputFile<<endl;
if (verbose) cout << "Save info client ["<<*id<<"]" << endl;
} // end of the the target loop
} // fin try
catch (Exception& e)
{
cout << e.toString().c_str() << endl;
}
return 0;
}
// Can use this function to get likelihood with a topgauss
double TopGauss::get(MixtureGD & UBM,FeatureServer &fs,String & featureFilename,Config & config){
StatServer ss(config);
String labelSelectedFrames =config.getParam("labelSelectedFrames");
unsigned long begin=fs.getFirstFeatureIndexOfASource(featureFilename);
fs.seekFeature(begin);
SegServer segmentsServer;
LabelServer labelServer;
initializeClusters(featureFilename,segmentsServer,labelServer,config);
// __android_log_print(ANDROID_LOG_DEBUG, "TopGauss::get", " Feature file %s \n", featureFilename.c_str());
verifyClusterFile(segmentsServer,fs,config);
unsigned long codeSelectedFrame=labelServer.getLabelIndexByString(labelSelectedFrames);
SegCluster& selectedSegments=segmentsServer.getCluster(codeSelectedFrame);
MixtureGDStat &acc=ss.createAndStoreMixtureStat(UBM);
Seg *seg; // current selected segment
selectedSegments.rewind();
unsigned long t=0; //cnt frames
acc.resetLLK();
unsigned long idxBegin=0;
while((seg=selectedSegments.getSeg())!=NULL){
unsigned long begin=seg->begin()+fs.getFirstFeatureIndexOfASource(seg->sourceName());
fs.seekFeature(begin);
Feature f;
idxBegin=this->frameToIdx(t);
for (unsigned long idxFrame=0;idxFrame<seg->length();idxFrame++){
fs.readFeature(f);
//unsigned long idx=this->frameToIdx(t);
unsigned long nbg=_nbg[t];
ULongVector index;
double sumNonSelectedWeights=_snsw[t];
double sumNonSelectedLLK=_snsl[t];
for (unsigned long i=0;i<nbg;i++) {
index.addValue(_idx[idxBegin+i]);
}
char c[100];
sprintf(c,"%d",(int)index.size());
config.setParam("topDistribsCount",c); // this should be high enough
if (t==0) {acc.computeAndAccumulateLLK(f,1.0,DETERMINE_TOP_DISTRIBS);acc.resetLLK();} // to remove in ALIZE, this is to init the LKvector
ss.setTopDistribIndexVector(index, sumNonSelectedWeights, sumNonSelectedLLK);
acc.computeAndAccumulateLLK(f,1.0,USE_TOP_DISTRIBS);
idxBegin+=nbg;
t++;
}
}
//ss.deleteMixtureStat(acc);
if (t!=_nt || idxBegin !=_nbgcnt) cout << "W: t("<<t<<") != _nt(" <<_nt<<")"<<"W: idxBegin("<<idxBegin<<") != _nbgcnt(" <<_nbgcnt<<")"<<endl;
return acc.getMeanLLK();
}
void cms(String & featureFileName,FeatureServer &fs,Config &config) {
unsigned long begin=fs.getFirstFeatureIndexOfASource(featureFileName);
fs.seekFeature(begin);
SegServer segmentsServer;
LabelServer labelServer;
initializeClusters(featureFileName,segmentsServer,labelServer,config);
verifyClusterFile(segmentsServer,fs,config);
unsigned long codeSelectedFrame=labelServer.getLabelIndexByString(config.getParam("labelSelectedFrames"));
SegCluster& selectedSegments=segmentsServer.getCluster(codeSelectedFrame);
selectedSegments.rewind();
RealVector <double> mean,cov;
FrameAccGD frameAccu;
frameAccu.reset();
accumulateStatFrame(frameAccu,fs, selectedSegments, config);
mean = frameAccu.getMeanVect(); // Get the mean vector
cov = frameAccu.getStdVect(); // Get the std vector
computeZeroOne(mean,cov,fs, selectedSegments, config);
}
// Main init function
double TopGauss::compute(MixtureGD & UBM,FeatureServer &fs,String & featureFilename,Config & config){
StatServer ss(config);
MixtureGDStat &acc=ss.createAndStoreMixtureStat(UBM);
unsigned long _mixsize=UBM.getDistribCount();
String labelSelectedFrames =config.getParam("labelSelectedFrames");
unsigned long begin=fs.getFirstFeatureIndexOfASource(featureFilename);
fs.seekFeature(begin);
SegServer segmentsServer;
LabelServer labelServer;
initializeClusters(featureFilename,segmentsServer,labelServer,config);
// __android_log_print(ANDROID_LOG_DEBUG, "TopGauss::compute", " Feature file %s \n", featureFilename.c_str());
verifyClusterFile(segmentsServer,fs,config);
unsigned long codeSelectedFrame=labelServer.getLabelIndexByString(labelSelectedFrames);
SegCluster& selectedSegments=segmentsServer.getCluster(codeSelectedFrame);
acc.resetLLK();
double topD=config.getParam("topGauss").toDouble();
if (verbose) {if(topD<1.0) cout << "LLK %="<< topD << "% ";else cout << "Top-"<<topD<<" ";}
// Class values
_nt=totalFrame(selectedSegments);
_nbg.setSize(_nt); _idx.setSize(0);_snsw.setSize(0); _snsl.setSize(0);
_nbg.setAllValues(0); _idx.setAllValues(0);_snsw.setAllValues(0.0);_snsl.setAllValues(0.0);
_nbgcnt=0;
Seg *seg; // current selected segment
selectedSegments.rewind();
unsigned long t=0; //cnt frames
while((seg=selectedSegments.getSeg())!=NULL){
unsigned long begin=seg->begin()+fs.getFirstFeatureIndexOfASource(seg->sourceName());
fs.seekFeature(begin);
Feature f;
for (unsigned long idxFrame=0;idxFrame<seg->length();idxFrame++){
fs.readFeature(f);
double llk=acc.computeAndAccumulateLLK(f,1.0,DETERMINE_TOP_DISTRIBS);
const LKVector &topV=ss.getTopDistribIndexVector();
double lk_tot=exp(llk);
double val=0.0;
if (topD<1.0) {
for(unsigned long j=0;j<_mixsize;j++){
if (val > topD*lk_tot) break;
val+=(topV[j].lk);
_nbg[t]++;
}
} else _nbg[t]=(unsigned long)topD;
_nbgcnt+=_nbg[t];
double snsw=1.0;
double snsl=lk_tot;
for(unsigned long j=0;j<_nbg[t];j++) {
_idx.addValue(topV[j].idx);
snsw -=UBM.weight(topV[j].idx);
snsl -=topV[j].lk;
}
_snsw.addValue(snsw);
if (snsl < EPS_LK)
_snsl.addValue(EPS_LK);
else _snsl.addValue(snsl);
t++;
}
}
if (t!=_nt) cout << "W: t("<<t<<") != _nt(" <<_nt<<")"<<endl;
return acc.getMeanLLK();
}
