marytts.tools.dbselection

Class CoverageDefinition

java.lang.Object

marytts.tools.dbselection.CoverageDefinition

public class CoverageDefinition
extends Object

Builds and manages the cover sets

Author:

Anna Hunecke

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	CoverageDefinition.CoverageStatistics

Constructor Summary

Constructors

Constructor and Description
CoverageDefinition(FeatureDefinition featDef, CoverageFeatureProvider cfProvider, String configFile) Build a new coverage definition and read in the config file

Method Summary

Methods

Modifier and Type	Method and Description
Set<String>	getAllPhones()
CoverageDefinition.CoverageStatistics	getCorpusStatistics() Get descriptive statistics for the full corpus.
CoverageFeatureProvider	getCoverageFeatureProvider()
Set<String>	getDiphonesInCorpus()
Set<String>	getPhonesInCorpus()
byte	getVectorValue(byte[] vectors, int vectorIndex, int valueIndex)
void	initialiseCoverage() Compute the coverage of the corpus, build and fill the cover sets.
void	printResultToLog(PrintWriter logOut)
void	printSelectionDistribution(String distributionFile, String developmentFile, boolean logDevelopment) Print statistics of the selected sentences and a table of coverage development over time
void	printSettings(PrintWriter out) Print the settings of the config file
void	printTextCorpusStatistics(PrintWriter out) Print a statistic of the unit distribution in the corpus
boolean	reachedMaxSimpleDiphones() Check if cover has maximum simple diphone coverage
boolean	reachedMaxSimpleProsody() Check if cover has maximum simple prosody coverage
void	readCoverageBin(String filename, int[] idSentenceList) Read the cover sets from the given file
void	updateCover(byte[] features) Add the feature vectors for one sentence to the cover
double	usefulnessOfFVs(byte[] featureVectors) Get the usefulness of the given feature vectors Usefulness of a feature vector is defined as the sum of the score for the feature vectors on all levels of the tree.
void	writeCoverageBin(String filename) Print the cover sets to the given file

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

CoverageDefinition

public CoverageDefinition(FeatureDefinition featDef,
                  CoverageFeatureProvider cfProvider,
                  String configFile)
                   throws Exception

Build a new coverage definition and read in the config file

Parameters:

featDef - the feature definition for the vectors

cfProvider - coverage feature provider

configFile - optionally, the coverage config file name. if this is null, default settings will be used.

Throws:

Exception - Exception

Method Detail

initialiseCoverage

public void initialiseCoverage()
                        throws IOException

Compute the coverage of the corpus, build and fill the cover sets. This will iterate once through the entire corpus, to compute the maximally achievable coverage with this corpus.

Throws:

IOException - IOException

getCorpusStatistics

public CoverageDefinition.CoverageStatistics getCorpusStatistics()

Get descriptive statistics for the full corpus. These values are independent of the selection of any sentences.

Returns:

cs

getPhonesInCorpus

public Set<String> getPhonesInCorpus()

getAllPhones

public Set<String> getAllPhones()

getDiphonesInCorpus

public Set<String> getDiphonesInCorpus()

printTextCorpusStatistics

public void printTextCorpusStatistics(PrintWriter out)
                               throws Exception

Print a statistic of the unit distribution in the corpus

Parameters:

out - the print writer to print to

Throws:

Exception - Exception

printSettings

public void printSettings(PrintWriter out)

Print the settings of the config file

Parameters:

out - the PrintWriter to print to

printSelectionDistribution

public void printSelectionDistribution(String distributionFile,
                              String developmentFile,
                              boolean logDevelopment)
                                throws Exception

Print statistics of the selected sentences and a table of coverage development over time

Parameters:

distributionFile - the file to print the statistics to

developmentFile - the file to print the coverage development to

logDevelopment - if true, print development file

Throws:

Exception - Exception

printResultToLog

public void printResultToLog(PrintWriter logOut)

updateCover

public void updateCover(byte[] features)

Add the feature vectors for one sentence to the cover

Parameters:

features - the feature vectors to add

reachedMaxSimpleDiphones

public boolean reachedMaxSimpleDiphones()

Check if cover has maximum simple diphone coverage

Returns:

true if cover has maximum simple diphone coverage

reachedMaxSimpleProsody

public boolean reachedMaxSimpleProsody()

Check if cover has maximum simple prosody coverage

Returns:

true if cover has maximum simple prosody coverage

usefulnessOfFVs

public double usefulnessOfFVs(byte[] featureVectors)

Get the usefulness of the given feature vectors Usefulness of a feature vector is defined as the sum of the score for the feature vectors on all levels of the tree. On each level, the score is the product of the two weights of the node. The first weight reflects the frequency/ inverted frequency of the value associated with the node in the corpus (→ frequencyWeight). The second weight reflects how much an instance of a feature vector containing the associated value is wanted in the cover (→ wantedWeight).

Parameters:

featureVectors - the feature vectors

Returns:

the usefulness

getCoverageFeatureProvider

public CoverageFeatureProvider getCoverageFeatureProvider()

getVectorValue

public byte getVectorValue(byte[] vectors,
                  int vectorIndex,
                  int valueIndex)

writeCoverageBin

public void writeCoverageBin(String filename)
                      throws Exception

Print the cover sets to the given file

Parameters:

filename - the file to print to

Throws:

Exception - Exception

readCoverageBin

public void readCoverageBin(String filename,
                   int[] idSentenceList)
                     throws Exception

Read the cover sets from the given file

Parameters:

filename - the file containing the cover sets

idSentenceList - the id of the sentence list

Throws:

Exception - Exception