/**
* Clustering.
*
* @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 clustering(
double threshold, ClusterSet clusterSet, AudioFeatureSet featureSet, Parameter parameter)
throws Exception {
String mask = parameter.getParameterSegmentationOutputFile().getMask();
String oldMethod = parameter.getParameterClustering().getMethodAsString();
double oldThreshold = parameter.getParameterClustering().getThreshold();
String oldModelKind = parameter.getParameterModel().getModelKindAsString();
int oldNumberOfComponent = parameter.getParameterModel().getNumberOfComponents();
// --- begin NEW v 1.14 / 4.16 / 4.18 / 4.20---
parameter.getParameterClustering().setMethod("h");
// parameter.getParameterClustering().setMethod("sr");
// --- end NEW v 1.14 ---
parameter.getParameterClustering().setThreshold(threshold);
logger.finer(
"method:"
+ parameter.getParameterClustering().getMethod()
+ " thr:"
+ parameter.getParameterClustering().getThreshold());
parameter.getParameterModel().setModelKind("FULL");
parameter.getParameterModel().setNumberOfComponents(1);
ClusterSet clustersHClust = MClust.make(featureSet, clusterSet, parameter, null);
if (parameter.getParameterDiarization().isSaveAllStep()) {
parameter.getParameterSegmentationOutputFile().setMask(mask + ".h.seg");
MainTools.writeClusterSet(parameter, clustersHClust, false);
}
parameter.getParameterSegmentation().setMethod(oldMethod);
parameter.getParameterModel().setNumberOfComponents(oldNumberOfComponent);
parameter.getParameterModel().setModelKind(oldModelKind);
parameter.getParameterClustering().setThreshold(oldThreshold);
parameter.getParameterSegmentationOutputFile().setMask(mask);
return clustersHClust;
}
/**
* Clustering linear.
*
* @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 clusteringLinear(
double threshold, ClusterSet clusterSet, AudioFeatureSet featureSet, Parameter parameter)
throws Exception {
String mask = parameter.getParameterSegmentationOutputFile().getMask();
String oldMethod = parameter.getParameterClustering().getMethodAsString();
double oldThreshold = parameter.getParameterClustering().getThreshold();
String oldModelKind = parameter.getParameterModel().getModelKindAsString();
int oldNumberOfComponent = parameter.getParameterModel().getNumberOfComponents();
parameter.getParameterModel().setModelKind("FULL");
parameter.getParameterModel().setNumberOfComponents(1);
parameter.getParameterClustering().setMethod("l");
parameter.getParameterClustering().setThreshold(threshold);
ClusterSet clustersLClust = MClust.make(featureSet, clusterSet, parameter, null);
if (parameter.getParameterDiarization().isSaveAllStep()) {
parameter.getParameterSegmentationOutputFile().setMask(mask + ".l.seg");
MainTools.writeClusterSet(parameter, clustersLClust, false);
}
parameter.getParameterSegmentation().setMethod(oldMethod);
parameter.getParameterModel().setNumberOfComponents(oldNumberOfComponent);
parameter.getParameterModel().setModelKind(oldModelKind);
parameter.getParameterClustering().setThreshold(oldThreshold);
parameter.getParameterSegmentationOutputFile().setMask(mask);
return clustersLClust;
}
/**
* Segmentation.
*
* @param method the method
* @param kind the kind
* @param clusterSet the cluster set
* @param featureSet the feature set
* @param parameter the parameter
* @return the cluster set
* @throws Exception the exception
*/
public ClusterSet segmentation(
String method,
String kind,
ClusterSet clusterSet,
AudioFeatureSet featureSet,
Parameter parameter)
throws Exception {
String mask = parameter.getParameterSegmentationOutputFile().getMask();
String oldMethod = parameter.getParameterSegmentation().getMethodAsString();
int oldNumberOfComponent = parameter.getParameterModel().getNumberOfComponents();
String oldModelKind = parameter.getParameterModel().getModelKindAsString();
parameter.getParameterSegmentation().setMethod(method);
parameter.getParameterModel().setNumberOfComponents(1);
parameter.getParameterModel().setModelKind(kind);
ClusterSet clustersSeg = new ClusterSet();
MSeg.make(featureSet, clusterSet, clustersSeg, parameter);
if (parameter.getParameterDiarization().isSaveAllStep()) {
parameter.getParameterSegmentationOutputFile().setMask(mask + ".s.seg");
MainTools.writeClusterSet(parameter, clustersSeg, false);
}
parameter.getParameterSegmentation().setMethod(oldMethod);
parameter.getParameterModel().setNumberOfComponents(oldNumberOfComponent);
parameter.getParameterModel().setModelKind(oldModelKind);
parameter.getParameterSegmentationOutputFile().setMask(mask);
return clustersSeg;
}
/**
* 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;
}
/**
* Gender.
*
* @param clusterSetBase the cluster set base
* @param clusterSet the cluster set
* @param featureSet the feature set
* @param parameter the parameter
* @return the cluster set
* @throws Exception the exception
*/
public ClusterSet gender(
ClusterSet clusterSetBase,
ClusterSet clusterSet,
AudioFeatureSet featureSet,
Parameter parameter)
throws Exception {
String mask = parameter.getParameterSegmentationOutputFile().getMask();
boolean oldByCluster = parameter.getParameterScore().isByCluster();
boolean oldGender = parameter.getParameterScore().isGender();
String FeatureFormat = "featureSetTransformation";
AudioFeatureSet featureSet2 =
loadFeature(featureSet, parameter, clusterSet, FeatureFormat + ",1:3:2:0:0:0,13,1:1:0:0");
String dir = "ester2";
InputStream genderInputStream = getClass().getResourceAsStream(dir + "/gender.gmms");
GMMArrayList genderVector =
MainTools.readGMMContainer(genderInputStream, parameter.getParameterModel());
parameter.getParameterScore().setByCluster(true);
parameter.getParameterScore().setGender(true);
ClusterSet clustersGender = MScore.make(featureSet2, clusterSet, genderVector, null, parameter);
if (parameter.getParameterDiarization().isSaveAllStep()) {
parameter.getParameterSegmentationOutputFile().setMask(mask + ".g.seg");
MainTools.writeClusterSet(parameter, clustersGender, false);
}
parameter.getParameterSegmentationOutputFile().setMask(mask);
parameter.getParameterScore().setByCluster(oldByCluster);
parameter.getParameterScore().setGender(oldGender);
return clustersGender;
}
/**
* 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;
}
/**
* Speaker clustering.
*
* @param threshold the threshold
* @param method the method
* @param clusterSetBase the cluster set base
* @param clustersSet the clusters set
* @param featureSet the feature set
* @param parameter the parameter
* @return the cluster set
* @throws Exception the exception
*/
public ClusterSet speakerClustering(
double threshold,
String method,
ClusterSet clusterSetBase,
ClusterSet clustersSet,
AudioFeatureSet featureSet,
Parameter parameter)
throws Exception {
String mask = parameter.getParameterSegmentationOutputFile().getMask();
String oldMethod = parameter.getParameterClustering().getMethodAsString();
double oldThreshold = parameter.getParameterClustering().getThreshold();
String oldEMControl = parameter.getParameterEM().getEMControl();
int oldNTop = parameter.getParameterTopGaussian().getScoreNTop();
String oldSpeechDetectorMethod = parameter.getParameterInputFeature().getSpeechMethodAsString();
double oldSpeechDetectorThreshold = parameter.getParameterInputFeature().getSpeechThreshold();
// ** bottom up hierarchical classification using GMMs
// ** one for each cluster, trained by MAP adaptation of a UBM composed of the fusion of
// 4x128GMM
// ** the feature normalization use feature mapping technique, after the cluster frames are
// centered and reduced
String dir = "ester2";
InputStream ubmInputStream = getClass().getResourceAsStream(dir + "/ubm.gmm");
GMMArrayList ubmVect =
MainTools.readGMMContainer(ubmInputStream, parameter.getParameterModel());
GMM ubm = ubmVect.get(0);
// int nbCep = ubm.getDimension() + 1;
String FeatureFormat = "featureSetTransformation";
parameter.getParameterInputFeature().setSpeechMethod("E");
parameter.getParameterInputFeature().setSpeechThreshold(0.1);
AudioFeatureSet featureSet2 =
loadFeature(
featureSet, parameter, clustersSet, FeatureFormat + ",1:3:2:0:0:0,13,1:1:300:4");
parameter.getParameterClustering().setMethod(method);
parameter.getParameterClustering().setThreshold(threshold);
parameter.getParameterEM().setEMControl("1,5,0.01");
parameter.getParameterTopGaussian().setScoreNTop(5);
// ---- Begin NEW v 1.13 ---
// if (parameter.parameterSpeechDetector.useSpeechDetection() == true) {
// MSpeechDetector.EnergyThresholdMethod(clustersSet, featureSet, parameter);
// }
// ---- End NEW v 1.13 ---
boolean saveAll = parameter.getParameterDiarization().isSaveAllStep();
parameter.getParameterDiarization().setSaveAllStep(false);
ClusterSet clustersCLR = MClust.make(featureSet2, clustersSet, parameter, ubm);
parameter.getParameterDiarization().setSaveAllStep(saveAll);
parameter.getParameterSegmentationOutputFile().setMask(mask);
if (parameter.getParameterDiarization().isSaveAllStep()) {
parameter.getParameterSegmentationOutputFile().setMask(mask + ".c.seg");
MainTools.writeClusterSet(parameter, clustersCLR, false);
}
parameter.getParameterSegmentationOutputFile().setMask(mask);
parameter.getParameterClustering().setMethod(oldMethod);
parameter.getParameterClustering().setThreshold(oldThreshold);
parameter.getParameterEM().setEMControl(oldEMControl);
parameter.getParameterTopGaussian().setScoreNTop(oldNTop);
parameter.getParameterInputFeature().setSpeechMethod(oldSpeechDetectorMethod);
parameter.getParameterInputFeature().setSpeechThreshold(oldSpeechDetectorThreshold);
return clustersCLR;
}
/**
* Speech.
*
* @param threshold the threshold
* @param clustersSetBase the clusters set base
* @param clustersSegInit the clusters seg init
* @param clustersDClust the clusters d clust
* @param featureSet the feature set
* @param parameter the parameter
* @return the cluster set
* @throws Exception the exception
*/
public ClusterSet speech(
String threshold,
ClusterSet clustersSetBase,
ClusterSet clustersSegInit,
ClusterSet clustersDClust,
AudioFeatureSet featureSet,
Parameter parameter)
throws Exception {
String mask = parameter.getParameterSegmentationOutputFile().getMask();
String oldDecoderPenalty = parameter.getParameterDecoder().getDecoderPenaltyAsString();
// ** Reload MFCC, remove energy and add delta
String FeatureFormat = "featureSetTransformation";
AudioFeatureSet featureSet2 =
loadFeature(
featureSet, parameter, clustersSetBase, FeatureFormat + ",1:3:2:0:0:0,13,0:0:0:0");
String dir = "ester2";
// ** load the model : 8 GMMs with 64 diagonal components
InputStream pmsInputStream = getClass().getResourceAsStream(dir + "/sms.gmms");
GMMArrayList pmsVect =
MainTools.readGMMContainer(pmsInputStream, parameter.getParameterModel());
// ** set penalties for the i to j states
// ** 10 for the first and second model corresponding to boad/narrowband silence
// ** 50 for the other jingle speech (f0 f2 f3 fx), jingle and music
parameter.getParameterDecoder().setDecoderPenalty(threshold);
ClusterSet clustersPMSClust = MDecode.make(featureSet2, clustersSegInit, pmsVect, parameter);
if (parameter.getParameterDiarization().isSaveAllStep()) {
parameter.getParameterSegmentationOutputFile().setMask(mask + ".sms.seg");
MainTools.writeClusterSet(parameter, clustersPMSClust, false);
}
parameter.getParameterSegmentationOutputFile().setMask(mask);
parameter.getParameterDecoder().setDecoderPenalty(oldDecoderPenalty);
// ** Filter the segmentation adj acoording the sms segmentation
// ** add 25 frames to all speech segments
// ** remove silence part if silence segment is less than 25 frames
// ** if a speech segment is less than 150 frames, it will be merge to the left or right closest
// segments
int oldSegmentPadding = parameter.getParameterFilter().getSegmentPadding();
int oldSilenceMinimumLength = parameter.getParameterFilter().getSilenceMinimumLength();
int oldSpeechMinimumLength = parameter.getParameterFilter().getSpeechMinimumLength();
String oldSegmentationFilterFile =
parameter.getParameterSegmentationFilterFile().getClusterFilterName();
parameter.getParameterFilter().setSegmentPadding(25);
parameter.getParameterFilter().setSilenceMinimumLength(25);
parameter.getParameterFilter().setSpeechMinimumLength(150);
ClusterSet clustersFltClust = SFilter.make(clustersDClust, clustersPMSClust, parameter);
if (parameter.getParameterDiarization().isSaveAllStep()) {
parameter.getParameterSegmentationOutputFile().setMask(mask + ".flt.seg");
MainTools.writeClusterSet(parameter, clustersFltClust, false);
parameter.getParameterSegmentationOutputFile().setMask(mask);
}
// ** segments of more than 20s are split according of silence present in the pms or using a gmm
// silence detector
InputStream silenceInputStream = getClass().getResourceAsStream(dir + "/s.gmms");
GMMArrayList sVect =
MainTools.readGMMContainer(silenceInputStream, parameter.getParameterModel());
parameter.getParameterSegmentationFilterFile().setClusterFilterName("iS,iT,j");
ClusterSet clustersSplitClust =
SSplitSeg.make(featureSet2, clustersFltClust, sVect, clustersPMSClust, parameter);
if (parameter.getParameterDiarization().isSaveAllStep()) {
parameter.getParameterSegmentationOutputFile().setMask(mask + ".spl.seg");
MainTools.writeClusterSet(parameter, clustersSplitClust, false);
parameter.getParameterSegmentationOutputFile().setMask(mask);
}
parameter.getParameterSegmentationFilterFile().setClusterFilterName(oldSegmentationFilterFile);
parameter.getParameterFilter().setSegmentPadding(oldSegmentPadding);
parameter.getParameterFilter().setSilenceMinimumLength(oldSilenceMinimumLength);
parameter.getParameterFilter().setSpeechMinimumLength(oldSpeechMinimumLength);
return clustersSplitClust;
}
