private boolean recalculateMedoids(
Map<Word, Integer> groups, List<Word> medoids, ClusterResult result) {
List<Word> temp = new ArrayList<>();
temp.addAll(medoids);
boolean changed = false;
double minCost = result.quality();
List<Word> nonMedoids = new ArrayList<>();
nonMedoids.addAll(words);
nonMedoids.removeAll(temp);
if (nonMedoids.size() == 0) return false;
// replace a random element in the medoids list with a random element in the non-medoids list
int index = new Random().nextInt(nonMedoids.size());
temp.set(new Random().nextInt(k), nonMedoids.get(index));
Map<Word, Integer> newGroups = groupPoints(temp);
double newCost = computeCost(temp, newGroups);
if (newCost < minCost) {
result = updateClusters(temp, newGroups, newCost);
changed = true;
}
return changed;
}
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();
}
}
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;
}