Package | Description |
---|---|
marytts.cart | |
marytts.cart.impose | |
marytts.cart.io | |
marytts.features | |
marytts.htsengine | |
marytts.tools.dbselection | |
marytts.tools.voiceimport | |
marytts.tools.voiceimport.traintrees | |
marytts.unitselection.data | |
marytts.unitselection.select | |
marytts.util |
Various relatively generic utilities.
|
Modifier and Type | Method and Description |
---|---|
FeatureVector[] |
LeafNode.FeatureVectorLeafNode.getFeatureVectors()
Get the feature vectors of this node
|
Modifier and Type | Method and Description |
---|---|
void |
LeafNode.FeatureVectorLeafNode.addFeatureVector(FeatureVector fv) |
String |
StringPredictionTree.getMostProbableString(FeatureVector aFV) |
Node |
DirectedGraphNode.getNextNode(FeatureVector fv) |
abstract Node |
DecisionNode.getNextNode(FeatureVector featureVector)
Select a daughter node according to the value in the given target
|
Node |
DecisionNode.BinaryByteDecisionNode.getNextNode(FeatureVector featureVector)
Select a daughter node according to the value in the given target
|
Node |
DecisionNode.BinaryShortDecisionNode.getNextNode(FeatureVector featureVector)
Select a daughter node according to the value in the given target
|
Node |
DecisionNode.BinaryFloatDecisionNode.getNextNode(FeatureVector featureVector)
Select a daughter node according to the value in the given target
|
Node |
DecisionNode.ByteDecisionNode.getNextNode(FeatureVector featureVector)
Select a daughter node according to the value in the given target
|
Node |
DecisionNode.ShortDecisionNode.getNextNode(FeatureVector featureVector)
Select a daughter node according to the value in the given target
|
Object |
DirectedGraph.interpret(FeatureVector fv)
Walk down the graph as far as possible according to the features in fv, and return the data in the leaf node found there.
|
protected Object |
DirectedGraph.interpret(Node n,
FeatureVector fv)
Follow the directed graph down to the most specific leaf with data, starting from node n.
|
Node |
StringPredictionTree.interpretToNode(FeatureVector featureVector,
int minNumberOfData)
TODO: copied from CART, does not work as expected with minNumberOfData = 0
Passes the given item through this CART and returns the leaf Node, or the Node it stopped walking down.
|
Node |
CART.interpretToNode(FeatureVector featureVector,
int minNumberOfData)
Passes the given item through this CART and returns the leaf Node, or the Node it stopped walking down.
|
void |
LeafNode.FeatureVectorLeafNode.setFeatureVectors(FeatureVector[] fv) |
Constructor and Description |
---|
LeafNode.FeatureVectorLeafNode(FeatureVector[] featureVectors)
Build a new leaf node containing the given feature vectors
|
Modifier and Type | Field and Description |
---|---|
FeatureVector[] |
FeatureFileIndexingResult.v |
Modifier and Type | Method and Description |
---|---|
FeatureVector[] |
FeatureArrayIndexer.getFeatureVectors(int from,
int to)
Get the feature vectors from the big array according to the given indices
|
Modifier and Type | Method and Description |
---|---|
int |
FeatureComparator.compare(FeatureVector a,
FeatureVector b)
Compares two feature vectors according to their values at an internal index previously set by this.setFeatureIdx().
|
FeatureFileIndexingResult |
FeatureArrayIndexer.retrieve(FeatureVector v)
Retrieve an array of unit features which complies with a specific target specification, according to an underlying tree.
|
FeatureFileIndexingResult |
FeatureArrayIndexer.retrieve(FeatureVector v,
int condition,
int parameter)
Retrieve an array of unit features which complies with a specific target specification, according to an underlying tree,
and given a stopping condition.
|
Constructor and Description |
---|
FeatureArrayIndexer(FeatureVector[] featureVectors,
FeatureDefinition featureDefinition)
Constructor which loads the feature vector array but does not launch an indexing operation.
|
FeatureArrayIndexer(FeatureVector[] featureVectors,
FeatureDefinition featureDefinition,
int[] setFeatureSequence)
Constructor which takes an array of feature vectors and launches an indexing operation according to a feature sequence
constraint.
|
FeatureArrayIndexer(FeatureVector[] featureVectors,
FeatureDefinition featureDefinition,
String[] setFeatureSequence)
Constructor which takes an array of feature vectors and launches an indexing operation according to a feature sequence
constraint.
|
FeatureFileIndexingResult(FeatureVector[] setV,
int setLevel) |
Modifier and Type | Method and Description |
---|---|
void |
WagonCARTReader.fillLeafs(Node root,
FeatureVector[] featureVectors)
Fill the FeatureVector leafs of a tree with the given feature vectors.
|
Modifier and Type | Method and Description |
---|---|
FeatureVector |
TargetFeatureComputer.computeFeatureVector(Target target)
Using the set of feature processors defined when creating the target feature computer, compute a feature vector for the
target
|
FeatureVector |
FeatureDefinition.createEdgeFeatureVector(int unitIndex,
boolean start)
Create a feature vector that marks a start or end of a unit.
|
FeatureVector |
FeatureDefinition.readFeatureVector(int currentUnitIndex,
ByteBuffer bb)
Create a feature vector consistent with this feature definition by reading the data from the byte buffer.
|
FeatureVector |
FeatureDefinition.readFeatureVector(int currentUnitIndex,
DataInput input)
Create a feature vector consistent with this feature definition by reading the data from the given input.
|
FeatureVector |
FeatureDefinition.toFeatureVector(int unitIndex,
byte[] bytes,
short[] shorts,
float[] floats) |
FeatureVector |
FeatureDefinition.toFeatureVector(int unitIndex,
String featureString)
Create a feature vector consistent with this feature definition by reading the data from a String representation.
|
Modifier and Type | Method and Description |
---|---|
static int |
FeatureDefinition.diff(FeatureVector v1,
FeatureVector v2)
Compares two feature vectors in terms of how many discrete features they have in common.
|
String |
FeatureDefinition.getFeatureValueAsString(String featureName,
FeatureVector fv)
Simple access to string-based features.
|
String |
FeatureDefinition.toFeatureString(FeatureVector fv)
Convert a feature vector into a String representation.
|
String |
TargetFeatureComputer.toStringValues(FeatureVector features)
For the given feature vector, convert each encoded value into its string representation.
|
Modifier and Type | Method and Description |
---|---|
String |
PhoneTranslator.features2context(FeatureDefinition def,
FeatureVector featureVector,
Vector<String> featureList)
Convert the feature vector into a context model name to be used by HTS/HTK.
|
String |
PhoneTranslator.features2LongContext(FeatureDefinition def,
FeatureVector featureVector,
Vector<String> featureList)
Convert the feature vector into a context model name to be used by HTS/HTK.
|
HTSModel |
CartTreeSet.generateHTSModel(HMMData htsData,
FeatureDefinition feaDef,
FeatureVector fv,
double oldErr)
creates a HTSModel (pre-HMM optimization vector data for all parameter streams of a given phoneme) given a feature vector
compare with original code in the main loop of marytts.modules.HTSEngine#processTargetList()
|
double |
CartTreeSet.searchDurInCartTree(HTSModel m,
FeatureVector fv,
HMMData htsData,
boolean firstPh,
boolean lastPh,
double diffdur) |
double |
CartTreeSet.searchDurInCartTree(HTSModel m,
FeatureVector fv,
HMMData htsData,
double diffdur)
Searches fv in durTree CART[] set of trees, per state, and fill the information in the HTSModel m.
|
void |
CartTreeSet.searchLf0InCartTree(HTSModel m,
FeatureVector fv,
FeatureDefinition featureDef,
double uvthresh)
Searches fv in Lf0Tree CART[] set of trees, per state, and fill the information in the HTSModel m.
|
void |
CartTreeSet.searchMagInCartTree(HTSModel m,
FeatureVector fv,
FeatureDefinition featureDef)
Searches fv in MagTree CART[] set of trees, per state, and fill the information in the HTSModel m.
|
void |
CartTreeSet.searchMgcInCartTree(HTSModel m,
FeatureVector fv,
FeatureDefinition featureDef)
Searches fv in mgcTree CART[] set of trees, per state, and fill the information in the HTSModel m.
|
void |
CartTreeSet.searchStrInCartTree(HTSModel m,
FeatureVector fv,
FeatureDefinition featureDef)
Searches fv in StrTree CART[] set of trees, per state, and fill the information in the HTSModel m.
|
Modifier and Type | Method and Description |
---|---|
static byte[] |
CoverageUtils.toCoverageFeatures(String featureNames,
FeatureDefinition def,
FeatureVector[] featureVectors)
Convert the given feature vectors to the coverage features format, containing all byte features in a single byte array.
|
Modifier and Type | Field and Description |
---|---|
protected FeatureVector[] |
CARTBuilder.WagonCallerThread.featureVectors |
Modifier and Type | Method and Description |
---|---|
void |
CARTBuilder.buildAndDumpDistanceTables(FeatureVector[] featureVectors,
String filename,
FeatureDefinition featDef)
Build the distance tables for the units from which we have the feature vectors and dump them to a file with the given
filename
|
void |
CARTBuilder.dumpFeatureVectors(FeatureVector[] featureVectors,
FeatureDefinition featDef,
String filename)
Dump the given feature vectors to a file with the given filename
|
Constructor and Description |
---|
CARTBuilder.WagonCallerThread(String id,
LeafNode leafToReplace,
FeatureDefinition featureDefinition,
FeatureVector[] featureVectors,
String descFilename,
String valueFilename,
String distanceTableFilename,
String cartFilename,
int balance,
int stop,
String ESTDIR) |
Modifier and Type | Method and Description |
---|---|
float[] |
F0ContourPolynomialDistanceMeasure.computeMean(FeatureVector[] fvs)
Compute the mean polynomial from the given set of polynomials.
|
double |
F0ContourPolynomialDistanceMeasure.computeVariance(FeatureVector[] fvs)
Compute the variance of the given set of feature vectors.
|
float |
F0ContourPolynomialDistanceMeasure.distance(FeatureVector fv1,
FeatureVector fv2)
Compute the distance between the f0 contours corresponding to the given feature vectors.
|
float |
DurationDistanceMeasure.distance(FeatureVector fv1,
FeatureVector fv2)
Compute the distance between the f0 contours corresponding to the given feature vectors.
|
float |
DistanceMeasure.distance(FeatureVector fv1,
FeatureVector fv2)
Compute the distance between two feature vectors.
|
float |
F0ContourPolynomialDistanceMeasure.squaredDistance(FeatureVector fv1,
FeatureVector fv2)
Compute the distance between the f0 contours corresponding to the given feature vectors.
|
float |
DurationDistanceMeasure.squaredDistance(FeatureVector fv1,
FeatureVector fv2)
Compute the distance between the f0 contours corresponding to the given feature vectors.
|
float |
DistanceMeasure.squaredDistance(FeatureVector fv1,
FeatureVector fv2)
Compute the squared distance between two feature vectors.
|
float |
F0ContourPolynomialDistanceMeasure.squaredDistance(FeatureVector fv,
float[] polynomial) |
Constructor and Description |
---|
AgglomerativeClusterer(FeatureVector[] features,
FeatureDefinition featureDefinition,
List<String> featuresToUse,
DistanceMeasure dist) |
AgglomerativeClusterer(FeatureVector[] features,
FeatureDefinition featureDefinition,
List<String> featuresToUse,
DistanceMeasure dist,
float proportionTestData) |
Wagon(String id,
FeatureDefinition featureDefinition,
FeatureVector[] featureVectors,
DistanceMeasure aDistanceMeasure,
File dir,
int balance,
int stop)
Set up a new wagon process.
|
Modifier and Type | Field and Description |
---|---|
protected FeatureVector[] |
FeatureFileReader.featureVectors |
Modifier and Type | Method and Description |
---|---|
FeatureVector[] |
FeatureFileReader.featureVectorMapping(FeatureDefinition newFeatureDefinition)
feature vector mapping according to new feature definition Note: The new feature definition should be a subset of original
feature definition
|
FeatureVector[] |
FeatureFileReader.getCopyOfFeatureVectors()
Return a shallow copy of the array of feature vectors.
|
FeatureVector |
FeatureFileReader.getFeatureVector(int unitIndex)
Get the unit feature vector for the given unit index number.
|
FeatureVector |
FeatureFileReader.getFeatureVector(Unit unit)
Get the unit feature vector for the given unit.
|
FeatureVector[] |
FeatureFileReader.getFeatureVectors()
Return the internal array of feature vectors.
|
Modifier and Type | Field and Description |
---|---|
protected FeatureVector |
Target.featureVector |
protected FeatureVector[] |
FFRTargetCostFunction.featureVectors |
Modifier and Type | Method and Description |
---|---|
FeatureVector |
Target.getFeatureVector() |
FeatureVector |
DiphoneTarget.getFeatureVector() |
FeatureVector |
TargetCostFunction.getFeatureVector(Unit unit)
Get the target cost feature vector for the given unit.
|
FeatureVector |
FFRTargetCostFunction.getFeatureVector(Unit unit)
Look up the features for a given unit.
|
FeatureVector |
DiphoneFFRTargetCostFunction.getFeatureVector(Unit unit) |
FeatureVector[] |
TargetCostFunction.getFeatureVectors()
Get all feature vectors.
|
FeatureVector[] |
FFRTargetCostFunction.getFeatureVectors() |
FeatureVector[] |
DiphoneFFRTargetCostFunction.getFeatureVectors() |
FeatureVector |
HalfPhoneFFRTargetCostFunction.getUnitFeatures(Unit unit)
Look up the features for a given unit.
|
Modifier and Type | Method and Description |
---|---|
void |
Target.setFeatureVector(FeatureVector featureVector) |
void |
DiphoneTarget.setFeatureVector(FeatureVector featureVector) |
Modifier and Type | Method and Description |
---|---|
static FeatureVector[] |
FeatureUtils.readFeatureVectors(String targetFeaturesData) |
Copyright © 2000–2016 DFKI GmbH. All rights reserved.