Modifier and Type | Field and Description |
---|---|
protected FeatureDefinition |
DirectedGraph.featDef |
protected FeatureDefinition |
DecisionNode.featureDefinition |
Modifier and Type | Method and Description |
---|---|
FeatureDefinition |
DirectedGraph.getFeatureDefinition() |
FeatureDefinition |
DecisionNode.getFeatureDefinition() |
Modifier and Type | Method and Description |
---|---|
void |
FeatureVectorCART.load(String fileName,
FeatureDefinition featDefinition,
String[] setFeatureSequence) |
String |
LeafNode.StringAndFloatLeafNode.mostProbableString(FeatureDefinition featureDefinition,
int featureIndex)
Return the most probable value in this leaf, translated into its string representation using the featureIndex'th
feature of the given feature definition.
|
Constructor and Description |
---|
CART(FeatureDefinition featDef)
Build a new empty cart with the given feature definition.
|
CART(Node rootNode,
FeatureDefinition featDef)
Build a new cart with the given node as the root node
|
CART(Node rootNode,
FeatureDefinition featDef,
Properties properties)
Build a new cart with the given node as the root node
|
DecisionNode.BinaryByteDecisionNode(int featureIndex,
byte value,
FeatureDefinition featureDefinition) |
DecisionNode.BinaryByteDecisionNode(int uniqueId,
FeatureDefinition featureDefinition)
Creates an empty BinaryByteDecisionNode, the feature and feature value of this node should be filled with
setFeatureAndFeatureValue() function.
|
DecisionNode.BinaryByteDecisionNode(String feature,
String value,
FeatureDefinition featureDefinition)
Create a new binary String DecisionNode.
|
DecisionNode.BinaryFloatDecisionNode(int featureIndex,
float value,
FeatureDefinition featureDefinition)
Create a new binary String DecisionNode.
|
DecisionNode.BinaryFloatDecisionNode(String feature,
float value,
FeatureDefinition featureDefinition) |
DecisionNode.BinaryShortDecisionNode(int featureIndex,
short value,
FeatureDefinition featureDefinition) |
DecisionNode.BinaryShortDecisionNode(String feature,
String value,
FeatureDefinition featureDefinition)
Create a new binary String DecisionNode.
|
DecisionNode.ByteDecisionNode(int featureIndex,
int numDaughters,
FeatureDefinition featureDefinition)
Build a new byte decision node
|
DecisionNode.ByteDecisionNode(String feature,
int numDaughters,
FeatureDefinition featureDefinition)
Build a new byte decision node
|
DecisionNode.ShortDecisionNode(int featureIndex,
int numDaughters,
FeatureDefinition featureDefinition)
Build a new short decision node
|
DecisionNode.ShortDecisionNode(String feature,
int numDaughters,
FeatureDefinition featureDefinition)
Build a new short decision node
|
DecisionNode(int numDaughters,
FeatureDefinition featureDefinition)
Construct a new DecisionNode
|
DecisionNode(int featureIndex,
int numDaughters,
FeatureDefinition featureDefinition)
Construct a new DecisionNode
|
DecisionNode(String feature,
int numDaughters,
FeatureDefinition featureDefinition)
Construct a new DecisionNode
|
DirectedGraph(FeatureDefinition featDef)
Build a new empty graph with the given feature definition.
|
DirectedGraph(Node rootNode,
FeatureDefinition featDef)
Build a new graph with the given node as the root node
|
DirectedGraph(Node rootNode,
FeatureDefinition featDef,
Properties properties)
Build a new graph with the given node as the root node
|
StringPredictionTree(BufferedReader reader,
FeatureDefinition featDefinition)
This constructs a new string prediction tree from a stream containing a tree in wagon format.
|
StringPredictionTree(Node aRootNode,
FeatureDefinition aFeatDef,
String[] aTargetDecoding) |
Modifier and Type | Method and Description |
---|---|
FeatureDefinition |
FeatureArrayIndexer.getFeatureDefinition() |
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.
|
Modifier and Type | Method and Description |
---|---|
Node |
WagonCARTReader.load(BufferedReader reader,
FeatureDefinition featDefinition)
This loads a cart from a wagon tree in textual format, from a reader.
|
CART[] |
HTSCARTReader.load(int numStates,
InputStream treeStream,
InputStream pdfStream,
HMMData.PdfFileFormat fileFormat,
FeatureDefinition featDefinition,
PhoneTranslator phTranslator)
Load the cart from the given file
|
Node |
WagonCARTReader.load(String fileName,
FeatureDefinition featDefinition,
String[] dummy)
Load the cart from the given file
|
Modifier and Type | Field and Description |
---|---|
protected FeatureDefinition |
TargetFeatureComputer.featureDefinition |
Modifier and Type | Method and Description |
---|---|
FeatureDefinition |
TargetFeatureComputer.getFeatureDefinition()
Provide the feature definition that can be used to interpret the feature processors generated by this
TargetFeatureComputer.
|
FeatureDefinition |
FeatureDefinition.subset(String[] featureNamesToDrop)
Create a new FeatureDefinition that contains a subset of the features in this.
|
Modifier and Type | Method and Description |
---|---|
boolean |
FeatureDefinition.contains(FeatureDefinition other)
Determine whether this FeatureDefinition is a superset of, or equal to, another FeatureDefinition.
|
boolean |
FeatureDefinition.featureEquals(FeatureDefinition other)
Determine whether two feature definitions are equal, with respect to number, names, and possible values of the three kinds
of features (byte-valued, short-valued, continuous).
|
String |
FeatureDefinition.featureEqualsAnalyse(FeatureDefinition other)
An extension of the previous method.
|
String |
FeatureVector.getFeatureAsString(int index,
FeatureDefinition feaDef)
A wrapper to getFeature(), to get the result as an String value, e.g., for subsequent System.out output.
|
Modifier and Type | Method and Description |
---|---|
FeatureDefinition |
HMMData.getFeatureDefinition() |
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()
|
void |
GVModelSet.loadGVModelSet(HMMData htsData,
FeatureDefinition featureDef) |
void |
GVModelSet.loadSwitchGvFromFile(String gvFile,
FeatureDefinition featDef,
PhoneTranslator trickyPhones) |
void |
CartTreeSet.loadTreeSet(HMMData htsData,
FeatureDefinition featureDef,
PhoneTranslator trickyPhones)
Loads all the CART trees
|
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 |
---|---|
FeatureDefinition |
SoP.getFeatureDefinition() |
Modifier and Type | Method and Description |
---|---|
double |
SoP.solve(Target t,
FeatureDefinition feaDef,
boolean log)
Solve the linear equation given the features (factors) in t and coeffs and factors in the SoP object * if interceptTterm =
TRUE solution = coeffs[0] + coeffs[1]*factors[0] + coeffs[2]*factors[1] + ...
|
double |
SoP.solve(Target t,
FeatureDefinition feaDef,
boolean log,
boolean debug) |
Constructor and Description |
---|
SoP(FeatureDefinition featDef)
Build a new empty sop with the given feature definition.
|
SoP(String line,
FeatureDefinition feaDef) |
Modifier and Type | Method and Description |
---|---|
FeatureDefinition |
UnitSelectionVoice.getF0CartsFeatDef() |
Modifier and Type | Field and Description |
---|---|
protected FeatureDefinition |
VoiceDataDumper.featureDefinition |
Modifier and Type | Field and Description |
---|---|
protected FeatureDefinition |
FeatureFileReader.featureDefinition |
protected FeatureDefinition |
HalfPhoneFeatureFileReader.leftWeights |
protected FeatureDefinition |
HalfPhoneFeatureFileReader.rightWeights |
Modifier and Type | Method and Description |
---|---|
FeatureDefinition |
FeatureFileReader.getFeatureDefinition() |
FeatureDefinition |
HalfPhoneFeatureFileReader.getLeftWeights() |
FeatureDefinition |
HalfPhoneFeatureFileReader.getRightWeights() |
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
|
Modifier and Type | Field and Description |
---|---|
protected FeatureDefinition |
FFRTargetCostFunction.featureDefinition |
protected FeatureDefinition |
HalfPhoneFFRTargetCostFunction.leftWeights |
protected FeatureDefinition |
HalfPhoneFFRTargetCostFunction.rightWeights |
Modifier and Type | Method and Description |
---|---|
FeatureDefinition |
TargetCostFunction.getFeatureDefinition()
Provide access to the Feature Definition used.
|
FeatureDefinition |
FFRTargetCostFunction.getFeatureDefinition() |
FeatureDefinition |
DiphoneFFRTargetCostFunction.getFeatureDefinition()
Provide access to the Feature Definition used.
|
Modifier and Type | Method and Description |
---|---|
protected double |
VocalizationFFRTargetCostFunction.cost(Target target,
Unit unit,
FeatureDefinition weights,
WeightFunc[] weightFunctions)
Compute the goodness-of-fit of a given unit for a given target
|
protected double |
FFRTargetCostFunction.cost(Target target,
Unit unit,
FeatureDefinition weights,
WeightFunc[] weightFunctions) |
protected double |
VocalizationFFRTargetCostFunction.featureCost(Target target,
Unit unit,
String featureName,
FeatureDefinition weights,
WeightFunc[] weightFunctions)
Compute the goodness-of-fit between given unit and given target for a given feature
|
protected double |
FFRTargetCostFunction.featureCost(Target target,
Unit unit,
String featureName,
FeatureDefinition weights,
WeightFunc[] weightFunctions) |
void |
JoinModelCost.setFeatureDefinition(FeatureDefinition def)
Set the feature definition to use for interpreting target feature vectors.
|
Constructor and Description |
---|
VocalizationFFRTargetCostFunction(VocalizationFeatureFileReader ffr,
FeatureDefinition fDef) |
Modifier and Type | Method and Description |
---|---|
static FeatureDefinition |
FeatureUtils.readFeatureDefinition(InputStream featureStream) |
static FeatureDefinition |
FeatureUtils.readFeatureDefinition(String targetFeaturesData) |
Modifier and Type | Field and Description |
---|---|
protected FeatureDefinition |
VocalizationSelector.f0FeatureDefinition |
protected FeatureDefinition |
VocalizationSelector.featureDefinition |
Modifier and Type | Method and Description |
---|---|
FeatureDefinition |
VocalizationSelector.getFeatureDefinition()
Get feature definition used to select suitable candidate
|
Copyright © 2000–2016 DFKI GmbH. All rights reserved.