/**
* 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;
}
/**
* 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;
}