/**
* 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;
}
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;
}