public void printTheBestByThr(long thr) {
System.out.println("------THE BEST BY SPEAKERil------");
Hashtable cluster = clusterResultSet.getCluster();
Iterator<String> it = cluster.keySet().iterator();
Hashtable<String, Vector> speaker = new Hashtable<String, Vector>();
while (it.hasNext()) {
String cr_it = (String) it.next();
// System.out.println(cr_it);
ClusterResult cr = (ClusterResult) cluster.get(cr_it);
Object[] db_arr = cr.getValue().keySet().toArray();
Arrays.sort(db_arr);
int ln = db_arr.length;
if (speaker.keySet().contains((String) cr.getValue().get(db_arr[ln - 1]))) {
Vector<String> tmp = speaker.get(cr.getValue().get(db_arr[ln - 1]));
tmp.add(cr_it);
speaker.put((String) cr.getValue().get(db_arr[ln - 1]), tmp);
} else {
Vector<String> tmp = new Vector<String>();
tmp.add(cr_it);
speaker.put((String) cr.getValue().get(db_arr[ln - 1]), tmp);
}
// System.out.println("score="+db_arr[ln-1] +" name="+cr.getValue().get(db_arr[ln-1]) );
}
Iterator<String> sp_it = speaker.keySet().iterator();
// String f
// ="/Users/labcontenuti/Documents/workspace/AudioActive/84/test_file/properties/testindent.txt";
OutputStreamWriter dos;
try {
dos =
new OutputStreamWriter(new FileOutputStream(outputRoot + "/" + baseName + "_ident.txt"));
while (sp_it.hasNext()) {
String key = (String) sp_it.next();
System.out.println("name=" + key);
for (int i = 0; i < ((Vector) speaker.get(key)).size(); i++) {
TreeMap<Integer, Segment> map =
clusterSetResult
.getCluster((String) ((Vector) speaker.get(key)).get(i))
.clusterToFrames();
System.out.println(
" cluster="
+ ((Vector) speaker.get(key)).get(i)
+ " lenght="
+ clusterSetResult
.getCluster((String) ((Vector) speaker.get(key)).get(i))
.getLength());
dos.write(((Vector) speaker.get(key)).get(i) + "=" + key + "\n");
}
}
dos.close();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
/**
* Decode.
*
* @param nbComp the nb comp
* @param threshold the threshold
* @param clusterSet the cluster set
* @param featureSet the feature set
* @param parameter the parameter
* @return the cluster set
* @throws Exception the exception
*/
public ClusterSet decode(
int nbComp,
double threshold,
ClusterSet clusterSet,
AudioFeatureSet featureSet,
Parameter parameter)
throws Exception {
String mask = parameter.getParameterSegmentationOutputFile().getMask();
String oldModelKind = parameter.getParameterModel().getModelKindAsString();
int oldNumberOfComponent = parameter.getParameterModel().getNumberOfComponents();
// ** Train GMM for each cluster.
// ** GMM is a 8 component gaussian with diagonal covariance matrix
// ** one GMM = one speaker = one cluster
// ** initialization of the GMMs :
// ** - same global covariance for each gaussian,
// ** - 1/8 for the weight,
// ** - means are initialized with the mean of 10 successive vectors taken
parameter.getParameterModel().setModelKind("DIAG");
parameter.getParameterModel().setNumberOfComponents(nbComp);
GMMArrayList gmmInitVect = new GMMArrayList(clusterSet.clusterGetSize());
MTrainInit.make(featureSet, clusterSet, gmmInitVect, parameter);
// ** EM training of the initialized GMM
GMMArrayList gmmVect = new GMMArrayList(clusterSet.clusterGetSize());
MTrainEM.make(featureSet, clusterSet, gmmInitVect, gmmVect, parameter);
// ** set the penalty to move from the state i to the state j, penalty to move from i to i is
// equal to 0
parameter.getParameterDecoder().setDecoderPenalty(String.valueOf(threshold));
// ** make Viterbi decoding using the 8-GMM set
// ** one state = one GMM = one speaker = one cluster
ClusterSet clustersDClust = MDecode.make(featureSet, clusterSet, gmmVect, parameter);
if (parameter.getParameterDiarization().isSaveAllStep()) {
parameter.getParameterSegmentationOutputFile().setMask(mask + ".d.seg");
MainTools.writeClusterSet(parameter, clustersDClust, false);
}
// ** move the boundaries of the segment in low energy part of the signal
ClusterSet clustersAdjClust = SAdjSeg.make(featureSet, clustersDClust, parameter);
if (parameter.getParameterDiarization().isSaveAllStep()) {
parameter.getParameterSegmentationOutputFile().setMask(mask + ".adj.seg");
MainTools.writeClusterSet(parameter, clustersAdjClust, false);
}
parameter.getParameterSegmentationOutputFile().setMask(mask);
parameter.getParameterModel().setNumberOfComponents(oldNumberOfComponent);
parameter.getParameterModel().setModelKind(oldModelKind);
return clustersAdjClust;
}
/**
* Sanity check.
*
* @param clusterSet the cluster set
* @param featureSet the feature set
* @param parameter the parameter
* @return the cluster set
* @throws DiarizationException the diarization exception
* @throws IOException Signals that an I/O exception has occurred.
* @throws ParserConfigurationException the parser configuration exception
* @throws SAXException the sAX exception
* @throws TransformerException the transformer exception
*/
public ClusterSet sanityCheck(
ClusterSet clusterSet, AudioFeatureSet featureSet, Parameter parameter)
throws DiarizationException, IOException, ParserConfigurationException, SAXException,
TransformerException {
String mask = parameter.getParameterSegmentationOutputFile().getMask();
ClusterSet clustersSegInit = new ClusterSet();
MSegInit.make(featureSet, clusterSet, clustersSegInit, parameter);
clustersSegInit.collapse();
if (parameter.getParameterDiarization().isSaveAllStep()) {
parameter.getParameterSegmentationOutputFile().setMask(mask + ".i.seg");
MainTools.writeClusterSet(parameter, clustersSegInit, false);
}
parameter.getParameterSegmentationOutputFile().setMask(mask);
return clustersSegInit;
}
/** Run. */
public void run() {
ClusterSet clusterSet = getNextClusterSet();
while (clusterSet != null) {
Parameter parameter = getParameter(arguments);
parameter.show = clusterSet.getShowNames().first();
logger.finer("-------------------------------------------");
logger.finer("--- " + parameter.show + " ---");
logger.finer("-------------------------------------------");
TreeMap<String, DiarizationResultList> showResult;
try {
showResult = tunEster2Diarization(parameter, clusterSet);
sumResult(showResult);
System.gc();
} catch (DiarizationException e) {
logger.log(Level.SEVERE, "Diarization error", e);
e.printStackTrace();
} catch (Exception e) {
logger.log(Level.SEVERE, "Exception error", e);
e.printStackTrace();
}
clusterSet = getNextClusterSet();
}
}
/**
* Initialize.
*
* @param parameter the parameter
* @return the cluster set
* @throws DiarizationException the diarization exception
* @throws Exception the exception
*/
public ClusterSet initialize(Parameter parameter) throws DiarizationException, Exception {
// ** get the first diarization
logger.info("Initialize segmentation");
ClusterSet clusterSet = null;
if (parameter.getParameterDiarization().isLoadInputSegmentation()) {
clusterSet = MainTools.readClusterSet(parameter);
// seg IRIT
// return clusterSet;
// seg IRIT
} else {
clusterSet = new ClusterSet();
Cluster cluster = clusterSet.createANewCluster("init");
Segment segment =
new Segment(
parameter.show,
0,
1,
cluster,
parameter.getParameterSegmentationInputFile().getRate());
cluster.addSegment(segment);
}
return clusterSet;
}
/**
* Tun ester2 speaker clr clustering.
*
* @param referenceClusterSet the reference cluster set
* @param uemClusterSet the uem cluster set
* @param partialKey the partial key
* @param method the method
* @param clusterSetBase the cluster set base
* @param clusterSet the cluster set
* @param featureSet the feature set
* @param parameter the parameter
* @return the diarization result list
* @throws Exception the exception
*/
public DiarizationResultList tunEster2SpeakerCLRClustering(
ClusterSet referenceClusterSet,
ClusterSet uemClusterSet,
String partialKey,
String method,
ClusterSet clusterSetBase,
ClusterSet clusterSet,
AudioFeatureSet featureSet,
Parameter parameter)
throws Exception {
String oldSpeechDetectorMethod = parameter.getParameterInputFeature().getSpeechMethodAsString();
double oldSpeechDetectorThreshold = parameter.getParameterInputFeature().getSpeechThreshold();
String oldModelKind = parameter.getParameterModel().getModelKindAsString();
int oldNumberOfComponent = parameter.getParameterModel().getNumberOfComponents();
String oldMethod = parameter.getParameterClustering().getMethodAsString();
double oldThreshold = parameter.getParameterClustering().getThreshold();
String oldEMControl = parameter.getParameterEM().getEMControl();
int oldNTop = parameter.getParameterTopGaussian().getScoreNTop();
boolean oldSaveAll = parameter.getParameterDiarization().isSaveAllStep();
DiarizationResultList localResult = new DiarizationResultList(cMin, cMax, mult);
DiarizationError computeError = new DiarizationError(referenceClusterSet, uemClusterSet);
double prevScore = cMin;
// ---- Begin NEW v 1.13 ---
parameter.getParameterInputFeature().setSpeechMethod("E");
parameter.getParameterInputFeature().setSpeechThreshold(0.1);
// ---- End NEW v 1.13 ---
String FeatureFormat = "featureSetTransformation";
String dir = "ester2";
InputStream ubmInputStream = getClass().getResourceAsStream(dir + "/ubm.gmm");
GMMArrayList ubmVect =
MainTools.readGMMContainer(ubmInputStream, parameter.getParameterModel());
GMM ubm = ubmVect.get(0);
/*
* int nbCep = 16; logger.info("---> nbCep:"+nbCep); FeatureSet featureSet2 = loadFeature(parameter, clusterSet, "audio16kHz2sphinx,1:3:2:0:0:0,"+nbCep+",1:1:300:4"); logger.info("---> nbCep:"+nbCep); //logger.fine("*** nbFeaturesNorm:" +
* clusterSetBase.getLength());
*/
// A tester
AudioFeatureSet featureSet2 =
loadFeature(featureSet, parameter, clusterSet, FeatureFormat + ",1:3:2:0:0:0,13,1:1:300:4");
// v5.14
// FeatureSet featureSet2 = loadFeature(featureSet, parameter, clusterSet, FeatureFormat
// + ",1:3:2:0:0:0,13,1:1:0:0");
parameter.getParameterModel().setModelKind("DIAG");
parameter.getParameterModel().setNumberOfComponents(ubm.getNbOfComponents());
parameter.getParameterClustering().setMethod(method);
// ---- Begin NEW v 1.19 ---
// parameter.getParameterEM().setEMControl("1,1,0.01");
// parameter.getParameterClustering().setThreshold(0);
// ---- End NEW v 1.19 ---
parameter.getParameterClustering().setThreshold(cMax);
parameter.getParameterEM().setEMControl("1,5,0.01");
parameter.getParameterTopGaussian().setScoreNTop(5);
parameter.getParameterDiarization().setSaveAllStep(false);
CLRHClustering clustering = new CLRHClustering(clusterSet, featureSet2, parameter, ubm);
// int nbCluster = clusterSet.clusterGetSize();
// logger.info("initialise clustering CLR clusterSet:"+clusterSet);
clustering.initialize();
double score = clustering.getScoreOfCandidatesForMerging();
DiarizationResult error = computeError.scoreOfMatchedSpeakers(clustering.getClusterSet());
double errorRate = error.getErrorRate();
localResult.setResult(prevScore, score, error);
// prevScore = Math.max(score, prevScore);
logger.fine(
"first "
+ parameter.show
+ " key="
+ partialKey
+ " clrScore="
+ score
+ " clrErrorRate="
+ errorRate
+ " clrSize="
+ clustering.getSize()
+ "/"
+ referenceClusterSet.clusterGetSize());
while ((score < cMax) && (clustering.getSize() > 1)) {
localResult.setResult(prevScore, score, error);
prevScore = Math.max(score, prevScore);
clustering.mergeCandidates();
// -- start V5.16 --
// logger.info("--> Decoding");
// ClusterSet decodeClusterSet = MDecode.make(featureSet2, clustering.getClusterSet(),
// clustering.getGmmList(), parameter);
// logger.info("--> Clustering");
// featureSet2 = loadFeature(featureSet, parameter, decodeClusterSet, FeatureFormat
// + ",1:3:2:0:0:0,13,1:1:300:4");
// clustering = new CLRHClustering(decodeClusterSet, featureSet2, parameter, ubm);
// clustering.initialize();
// -- end V5.16 --
score = clustering.getScoreOfCandidatesForMerging();
error = computeError.scoreOfMatchedSpeakers(clustering.getClusterSet());
errorRate = error.getErrorRate();
// localResult.setResult(prevScore, score, error);
// prevScore = Math.max(score, prevScore);
logger.fine(
parameter.show
+ " key="
+ partialKey
+ " clrScore="
+ score
+ " clrErrorRate="
+ errorRate
+ " clrSize="
+ clustering.getSize()
+ "/"
+ referenceClusterSet.clusterGetSize());
}
localResult.setResult(prevScore, score, error);
localResult.setResult(score, cMax, error);
logger.finer(parameter.show + " key=" + partialKey + " resultat du fichier");
localResult.log("partial result: " + parameter.show + " " + partialKey);
clustering.reset();
parameter.getParameterModel().setNumberOfComponents(oldNumberOfComponent);
parameter.getParameterModel().setModelKind(oldModelKind);
parameter.getParameterClustering().setMethod(oldMethod);
parameter.getParameterClustering().setThreshold(oldThreshold);
parameter.getParameterEM().setEMControl(oldEMControl);
parameter.getParameterTopGaussian().setScoreNTop(oldNTop);
parameter.getParameterInputFeature().setSpeechMethod(oldSpeechDetectorMethod);
parameter.getParameterInputFeature().setSpeechThreshold(oldSpeechDetectorThreshold);
parameter.getParameterDiarization().setSaveAllStep(oldSaveAll);
return localResult;
}
/**
* Tun ester2 diarization.
*
* @param parameter the parameter
* @param clusterSet the cluster set
* @return the tree map
* @throws DiarizationException the diarization exception
* @throws Exception the exception
*/
public TreeMap<String, DiarizationResultList> tunEster2Diarization(
Parameter parameter, ClusterSet clusterSet) throws DiarizationException, Exception {
TreeMap<String, DiarizationResultList> result = new TreeMap<String, DiarizationResultList>();
// double paramThr = parameter.getParameterClustering().getThreshold();
lMin = parameter.getParameterDiarization().getThreshold("l");
lMax = parameter.getParameterDiarization().getMaxThreshold("l");
hMin = parameter.getParameterDiarization().getThreshold("h");
hMax = parameter.getParameterDiarization().getMaxThreshold("h");
dMin = parameter.getParameterDiarization().getThreshold("d");
dMax = parameter.getParameterDiarization().getMaxThreshold("d");
cMin = parameter.getParameterDiarization().getThreshold("c");
cMax = parameter.getParameterDiarization().getMaxThreshold("c");
String featureDesc = parameter.getParameterInputFeature().getFeaturesDescriptorAsString();
AudioFeatureSet featureSet = null;
ClusterSet clustersSegInit = null;
if (parameter.getParameterDiarization().isLoadInputSegmentation() == false) {
featureSet = loadFeature(parameter, clusterSet, featureDesc);
featureSet.setCurrentShow(parameter.show);
int nbFeatures = featureSet.getNumberOfFeatures();
clusterSet.getFirstCluster().firstSegment().setLength(nbFeatures);
clustersSegInit = sanityCheck(clusterSet, featureSet, parameter);
} else {
featureSet = loadFeature(parameter, clusterSet, featureDesc);
featureSet.setCurrentShow(parameter.show);
clustersSegInit = sanityCheck(clusterSet, featureSet, parameter);
featureSet = loadFeature(parameter, clustersSegInit, featureDesc);
featureSet.setCurrentShow(parameter.show);
}
// seg IRIT
// ClusterSet clustersSegSave = clustersSegInit;
// seg IRIT
ClusterSet referenceClusterSet = MainTools.readTheSecondClusterSet(parameter);
ClusterSet uemClusterSet = MainTools.readThe3rdClusterSet(parameter);
if (parameter.getParameterDiarization().isLastStepOnly()) {
String key = "l=" + lMin + " h=" + hMin + " d=" + dMin;
DiarizationResultList values = null;
if (parameter.getParameterDiarization().isCEClustering() == false) {
logger.warning(" nothing to do isCEClustering == false");
} else {
values =
tunEster2SpeakerCLRClustering(
referenceClusterSet,
uemClusterSet,
key,
"ce",
clusterSet,
clusterSet,
featureSet,
parameter);
}
result.put(key, values);
return result;
}
ClusterSet clustersSegSave =
segmentation("GLR", "FULL", clustersSegInit, featureSet, parameter);
for (double l = lMin; l <= lMax; l += 0.5) {
ClusterSet clustersSeg = clustersSegSave.clone();
logger.finest("clustering l=" + l);
ClusterSet clustersLClust = clusteringLinear(l, clustersSeg, featureSet, parameter);
// ---- Begin NEW v 1.14 ---
for (double h = hMin; h <= hMax; h += 0.5) {
// for (double h = hMin; h <= hMax; h += 0.2) {
// ---- end NEW v 1.14 ---
// if (h > l) {
ClusterSet clustersHClust = clustering(h, clustersLClust, featureSet, parameter);
for (double d = dMin; d <= dMax; d += 50) {
ClusterSet clustersDClust = decode(8, d, clustersHClust, featureSet, parameter);
// double error = DiarizationError.scoreOfMatchedSpeakers(referenceClusterSet,
// clustersDClust);
ClusterSet clustersSplitClust =
speech(
"10,10,50", clusterSet, clustersSegInit, clustersDClust, featureSet, parameter);
ClusterSet clustersGender = gender(clusterSet, clustersSplitClust, featureSet, parameter);
String key = "l=" + l + " h=" + h + " d=" + d;
DiarizationResultList values = null;
if (parameter.getParameterDiarization().isCEClustering() == false) {
values = new DiarizationResultList(0, 0, 1);
DiarizationError computeError =
new DiarizationError(referenceClusterSet, uemClusterSet);
DiarizationResult error = computeError.scoreOfMatchedSpeakers(clustersGender);
values.setResult(0, 0, error);
logger.finer(parameter.show + " key=" + key + " resultat du fichier");
values.log("partial result: " + parameter.show + " " + key);
} else {
// V4.19 = CLUST_H_BIC_GMM_MAP
// values = tunEster2SpeakerCLRClustering(referenceClusterSet, key, "bicgmmmap",
// clustersGender, clustersGender, featureSet, parameter);
// V5.16 = ce_d
// values = tunEster2SpeakerCLRClustering(referenceClusterSet, key, "ce_d",
// clustersGender, clustersGender, featureSet, parameter);
values =
tunEster2SpeakerCLRClustering(
referenceClusterSet,
uemClusterSet,
key,
"ce",
clustersGender,
clustersGender,
featureSet,
parameter);
}
if (result.containsKey(key)) {
result.get(key).addResultArray(values);
} else {
result.put(key, values);
}
}
// }
}
}
return result;
}
/**
* Ester2 version.
*
* @param parameter the parameter
* @throws DiarizationException the diarization exception
* @throws Exception the exception
*/
public void ester2Version(Parameter parameter) throws DiarizationException, Exception {
// ** Caution this system is developed using Sphinx MFCC computed with legacy mode
ClusterSet referenceClusterSet = null;
if (!parameter.getParameterSegmentationInputFile2().getMask().equals("")) {
referenceClusterSet = MainTools.readTheSecondClusterSet(parameter);
}
ClusterSet uemClusterSet = null;
if (!parameter.getParameterSegmentationInputFile3().getMask().equals("")) {
referenceClusterSet = MainTools.readThe3rdClusterSet(parameter);
}
ParameterBNDiarization parameterDiarization = parameter.getParameterDiarization();
// ** mask for the output of the segmentation file
ClusterSet clusterSet = initialize(parameter);
// ** load the features, sphinx format (13 MFCC with C0) or compute it form a wave file
AudioFeatureSet featureSet =
loadFeature(
parameter,
clusterSet,
parameter.getParameterInputFeature().getFeaturesDescriptorAsString());
featureSet.setCurrentShow(parameter.show);
int nbFeatures = featureSet.getNumberOfFeatures();
if (parameter.getParameterDiarization().isLoadInputSegmentation() == false) {
clusterSet.getFirstCluster().firstSegment().setLength(nbFeatures);
}
// clusterSet.debug(3);
ClusterSet clustersSegInit = sanityCheck(clusterSet, featureSet, parameter);
ClusterSet clustersSeg = segmentation("GLR", "FULL", clustersSegInit, featureSet, parameter);
// Seg IRIT
// ClusterSet clustersSegInit = clusterSet;
// ClusterSet clustersSeg = clusterSet;
// Seg IRIT
ClusterSet clustersLClust =
clusteringLinear(
parameterDiarization.getThreshold("l"), clustersSeg, featureSet, parameter);
ClusterSet clustersHClust =
clustering(parameterDiarization.getThreshold("h"), clustersLClust, featureSet, parameter);
// MainTools.writeClusterSet(parameter, clustersHClust, false);
ClusterSet clustersDClust =
decode(8, parameterDiarization.getThreshold("d"), clustersHClust, featureSet, parameter);
ClusterSet clustersSplitClust =
speech("10,10,50", clusterSet, clustersSegInit, clustersDClust, featureSet, parameter);
ClusterSet clustersGender = gender(clusterSet, clustersSplitClust, featureSet, parameter);
if (parameter.getParameterDiarization().isCEClustering()) {
ClusterSet clustersCLR =
speakerClustering(
parameterDiarization.getThreshold("c"),
"ce",
clustersSegInit,
clustersGender,
featureSet,
parameter);
MainTools.writeClusterSet(parameter, clustersCLR, false);
if (referenceClusterSet != null) {
DiarizationError computeError = new DiarizationError(referenceClusterSet, uemClusterSet);
computeError.scoreOfMatchedSpeakers(clustersCLR);
}
} else {
MainTools.writeClusterSet(parameter, clustersGender, false);
}
}
public ClusterSet make(
AudioFeatureSet featureSet,
ClusterSet clusterSet,
GMMArrayList gmmList,
GMMArrayList gmmTopList,
Parameter parameter)
throws DiarizationException, IOException {
logger.info("Compute Score");
int size = gmmList.size();
logger.finer("GMM size:" + size);
ArrayList<String> genderString = new ArrayList<String>();
ArrayList<String> bandwidthString = new ArrayList<String>();
for (int i = 0; i < size; i++) {
String gmmName = gmmList.get(i).getName();
if (parameter.getParameterScore().isGender() == true) {
if (gmmName.equals("MS")) {
genderString.add(Cluster.genderStrings[1]);
bandwidthString.add(Segment.bandwidthStrings[2]);
} else if (gmmName.equals("FS")) {
genderString.add(Cluster.genderStrings[2]);
bandwidthString.add(Segment.bandwidthStrings[2]);
} else if (gmmName.equals("MT")) {
genderString.add(Cluster.genderStrings[1]);
bandwidthString.add(Segment.bandwidthStrings[1]);
} else if (gmmName.equals("FT")) {
genderString.add(Cluster.genderStrings[2]);
bandwidthString.add(Segment.bandwidthStrings[1]);
} else {
genderString.add(Cluster.genderStrings[0]);
bandwidthString.add(Segment.bandwidthStrings[0]);
}
} else {
genderString.add(Cluster.genderStrings[0]);
bandwidthString.add(Segment.bandwidthStrings[0]);
}
}
ClusterSet clusterSetResult = new ClusterSet();
for (Cluster cluster : clusterSet.clusterSetValue()) {
double[] sumScoreVector = new double[size];
int[] sumLenghtVector = new int[size];
double ubmScore = 0.0;
GMM gmmTop = null;
if (parameter.getParameterTopGaussian().getScoreNTop() >= 0) {
gmmTop = gmmTopList.get(0);
}
Arrays.fill(sumScoreVector, 0.0);
Arrays.fill(sumLenghtVector, 0);
for (Segment currantSegment : cluster) {
Segment segment = (currantSegment.clone());
int end = segment.getStart() + segment.getLength();
featureSet.setCurrentShow(segment.getShowName());
double[] scoreVector = new double[size];
double maxScore = 0.0;
int idxMaxScore = 0;
for (int i = 0; i < size; i++) {
gmmList.get(i).score_initialize();
}
for (int start = segment.getStart(); start < end; start++) {
for (int i = 0; i < size; i++) {
GMM gmm = gmmList.get(i);
if (parameter.getParameterTopGaussian().getScoreNTop() >= 0) {
if (i == 0) {
gmmTop.score_getAndAccumulateAndFindTopComponents(
featureSet, start, parameter.getParameterTopGaussian().getScoreNTop());
}
gmm.score_getAndAccumulateForComponentSubset(
featureSet, start, gmmTop.getTopGaussianVector());
} else {
gmm.score_getAndAccumulate(featureSet, start);
}
}
}
if (parameter.getParameterTopGaussian().getScoreNTop() >= 0) {
ubmScore = gmmTop.score_getMeanLog();
gmmTop.score_getSumLog();
gmmTop.score_getCount();
gmmTop.score_reset();
}
for (int i = 0; i < size; i++) {
GMM gmm = gmmList.get(i);
scoreVector[i] = gmm.score_getMeanLog();
sumLenghtVector[i] += gmm.score_getCount();
sumScoreVector[i] += gmm.score_getSumLog();
if (i == 0) {
maxScore = scoreVector[0];
idxMaxScore = 0;
} else {
double value = scoreVector[i];
if (maxScore < value) {
maxScore = value;
idxMaxScore = i;
}
}
gmm.score_reset();
}
if (parameter.getParameterScore().isTNorm()) {
double sumScore = 0;
double sum2Score = 0;
for (int i = 0; i < size; i++) {
sumScore += scoreVector[i];
sum2Score += (scoreVector[i] * scoreVector[i]);
}
for (int i = 0; i < size; i++) {
double value = scoreVector[i];
double mean = (sumScore - value) / (size - 1);
double et = Math.sqrt(((sum2Score - (value * value)) / (size - 1)) - (mean * mean));
scoreVector[i] = (value - mean) / et;
}
}
if (parameter.getParameterScore().isGender() == true) {
segment.setBandwidth(bandwidthString.get(idxMaxScore));
segment.setInformation("segmentGender", genderString.get(idxMaxScore));
}
if (parameter.getParameterScore().isBySegment()) {
for (int k = 0; k < size; k++) {
double score = scoreVector[k];
GMM gmm = gmmList.get(k);
segment.setInformation("score:" + gmm.getName(), score);
currantSegment.setInformation("score:" + gmm.getName(), score);
}
if (parameter.getParameterTopGaussian().getScoreNTop() >= 0) {
segment.setInformation("score:" + "UBM", ubmScore);
currantSegment.setInformation("score:" + "UBM", ubmScore);
}
}
String newName = cluster.getName();
if (parameter.getParameterScore().isByCluster() == false) {
if ((scoreVector[idxMaxScore] > parameter.getParameterSegmentation().getThreshold())
&& (parameter.getParameterScore().getLabel()
!= ParameterScore.LabelType.LABEL_TYPE_NONE.ordinal())) {
if (parameter.getParameterScore().getLabel()
== ParameterScore.LabelType.LABEL_TYPE_ADD.ordinal()) {
newName += "_";
newName += gmmList.get(idxMaxScore).getName();
} else {
newName = gmmList.get(idxMaxScore).getName();
}
}
Cluster temporaryCluster = clusterSetResult.getOrCreateANewCluster(newName);
temporaryCluster.setGender(cluster.getGender());
if (parameter.getParameterScore().isGender() == true) {
temporaryCluster.setGender(genderString.get(idxMaxScore));
}
temporaryCluster.addSegment(segment);
}
}
if (parameter.getParameterScore().isByCluster()) {
for (int i = 0; i < size; i++) {
sumScoreVector[i] /= sumLenghtVector[i];
}
if (parameter.getParameterScore().isTNorm()) {
double sumScore = 0;
double sum2Score = 0;
for (int i = 0; i < size; i++) {
sumScore += sumScoreVector[i];
sum2Score += (sumScoreVector[i] * sumScoreVector[i]);
}
for (int i = 0; i < size; i++) {
double value = sumScoreVector[i];
double mean = (sumScore - value) / (size - 1);
double et = Math.sqrt(((sum2Score - (value * value)) / (size - 1)) - (mean * mean));
sumScoreVector[i] = (value - mean) / et;
}
}
double maxScore = sumScoreVector[0];
int idxMaxScore = 0;
for (int i = 1; i < size; i++) {
double s = sumScoreVector[i];
if (maxScore < s) {
maxScore = s;
idxMaxScore = i;
}
}
String newName = cluster.getName();
if ((sumScoreVector[idxMaxScore] > parameter.getParameterSegmentation().getThreshold())
&& (parameter.getParameterScore().getLabel()
!= ParameterScore.LabelType.LABEL_TYPE_NONE.ordinal())) {
if (parameter.getParameterScore().getLabel()
== ParameterScore.LabelType.LABEL_TYPE_ADD.ordinal()) {
newName += "_";
newName += gmmList.get(idxMaxScore).getName();
} else {
newName = gmmList.get(idxMaxScore).getName();
}
// logger.finer("cluster name=" + cluster.getName() + " new_name=" + newName);
}
Cluster tempororaryCluster = clusterSetResult.getOrCreateANewCluster(newName);
tempororaryCluster.setGender(cluster.getGender());
if (parameter.getParameterScore().isGender() == true) {
tempororaryCluster.setGender(genderString.get(idxMaxScore));
}
tempororaryCluster.setName(newName);
for (Segment currantSegment : cluster) {
Segment segment = (currantSegment.clone());
if (parameter.getParameterScore().isGender() == true) {
segment.setBandwidth(bandwidthString.get(idxMaxScore));
}
tempororaryCluster.addSegment(segment);
}
for (int k = 0; k < size; k++) {
double score = sumScoreVector[k];
GMM gmm = gmmList.get(k);
// logger.finer("****clustername = " + newName + " name=" + gmm.getName() + " =" + score+"
// k="+k);
// logger.log(Level.SEVERE, "****clustername = " + newName + " name=" + gmm.getName() + "
// =" + score);
tempororaryCluster.setInformation("score:" + gmm.getName(), score);
ClusterResult cr = new ClusterResult();
cr.setName(newName);
cr.getValue().put(score, gmm.getName());
System.out.println(
"------ clusterResultSet.putValue(newName, gmm.getName(), score)=----------------");
System.out.println(newName + " " + gmm.getName() + " " + score);
if (isName(gmm.getName())) {
clusterResultSet.putValue(newName, gmm.getName(), score);
} else {
System.out.println("*****************" + gmm.getName() + " Non nome valido ");
}
}
if (parameter.getParameterTopGaussian().getScoreNTop() >= 0) {
// tempororaryCluster.putInformation("score:" + "length", ubmSumLen);
// tempororaryCluster.putInformation("score:" + "UBM", ubmSumScore / ubmSumLen);
}
}
}
this.clusterSetResult = clusterSetResult;
return clusterSetResult;
}
