marytts.vocalizations

Class FDPSOLASynthesisTechnology

java.lang.Object

marytts.vocalizations.VocalizationSynthesisTechnology

marytts.vocalizations.FDPSOLASynthesisTechnology

public class FDPSOLASynthesisTechnology
extends VocalizationSynthesisTechnology

FDPSOLA Synthesis technology to synthesize vocalizations

Author:

Sathish Pammi

Field Summary

Fields

Modifier and Type	Field and Description
protected TimelineReader	audioTimeline
protected boolean	f0ContourImposeSupport
protected VocalizationUnitFileReader	unitFileReader
protected VocalizationIntonationReader	vIntonationReader

Constructor Summary

Constructors

Constructor and Description
FDPSOLASynthesisTechnology(String waveTimeLineFile, String unitFile, String intonationFeatureFile, boolean imposeF0Support)
FDPSOLASynthesisTechnology(TimelineReader audioTimeline, VocalizationUnitFileReader unitFileReader, HNMFeatureFileReader vHNMFeaturesReader, VocalizationIntonationReader vIntonationReader, boolean imposeF0Support)

Method Summary

Methods

Modifier and Type	Method and Description
AudioInputStream	reSynthesize(int backchannelNumber, AudioFileFormat aft) Re-synthesize given vocalization using FDPSOLA technology
AudioInputStream	synthesize(int backchannelNumber, AudioFileFormat aft) Synthesize given vocalization (i.e.
AudioInputStream	synthesizeUsingImposedF0(int sourceIndex, int targetIndex, AudioFileFormat aft) Impose target intonation contour on given vocalization using HNM technology

Methods inherited from class java.lang.Object

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

Field Detail

vIntonationReader

protected VocalizationIntonationReader vIntonationReader

audioTimeline

protected TimelineReader audioTimeline

unitFileReader

protected VocalizationUnitFileReader unitFileReader

f0ContourImposeSupport

protected boolean f0ContourImposeSupport

Constructor Detail

FDPSOLASynthesisTechnology

public FDPSOLASynthesisTechnology(String waveTimeLineFile,
                          String unitFile,
                          String intonationFeatureFile,
                          boolean imposeF0Support)
                           throws MaryConfigurationException

Throws:

MaryConfigurationException

FDPSOLASynthesisTechnology

public FDPSOLASynthesisTechnology(TimelineReader audioTimeline,
                          VocalizationUnitFileReader unitFileReader,
                          HNMFeatureFileReader vHNMFeaturesReader,
                          VocalizationIntonationReader vIntonationReader,
                          boolean imposeF0Support)

Method Detail

synthesize

public AudioInputStream synthesize(int backchannelNumber,
                          AudioFileFormat aft)
                            throws SynthesisException

Synthesize given vocalization (i.e. unit-selection)

Specified by:

synthesize in class VocalizationSynthesisTechnology

Parameters:

backchannelNumber - unit index

aft - audio file format

Returns:

AudioInputStream of synthesized vocalization

Throws:

SynthesisException - if failed to synthesize vocalization

reSynthesize

public AudioInputStream reSynthesize(int backchannelNumber,
                            AudioFileFormat aft)
                              throws SynthesisException

Re-synthesize given vocalization using FDPSOLA technology

Specified by:

reSynthesize in class VocalizationSynthesisTechnology

Parameters:

backchannelNumber - unit index

aft - audio file format

Returns:

AudioInputStream of synthesized vocalization

Throws:

SynthesisException - if failed to synthesize vocalization

synthesizeUsingImposedF0

public AudioInputStream synthesizeUsingImposedF0(int sourceIndex,
                                        int targetIndex,
                                        AudioFileFormat aft)
                                          throws SynthesisException

Impose target intonation contour on given vocalization using HNM technology

Specified by:

synthesizeUsingImposedF0 in class VocalizationSynthesisTechnology

Parameters:

sourceIndex - unit index of vocalization

targetIndex - unit index of target intonation

aft - audio file format

Returns:

AudioInputStream of synthesized vocalization

Throws:

SynthesisException - if failed to synthesize vocalization