Package | Description |
---|---|
marytts.signalproc.adaptation |
Packages for speaking style and speaker identity adaptation in Mary TTS
supporting various voice conversion algorithms.
|
marytts.signalproc.adaptation.prosody |
Prosody transformation algorithms for voice conversion.
A prosody modification framework has been implemented which supports: Mean and standard deviation transformation of f0 Sentence slope transformation Mean and standard deviation transformation is the best method so far. Duration and energy transformation have not yet been implemented. |
marytts.signalproc.analysis |
A collection of analysis algorithms for signal processing.
Important classes are as follows: LpcAnalyser: Linear prediction analysis using autocorrelation appraoch and Durbin recursion LsfAnalyser: Computation of line spectral frequencies (LSFs, or line spectral pairs - LSPs) based on LpcAnalyser EnergyAnalyser: Energy contour estimation with voice activity detection support F0TrackerAutocorrelationHeuristic: An autocorrelation based f0 analysis algorithm extended with heuristic post-processing to reduce voiced/unvoiced errors and f0 doubling/halving problems. |
marytts.signalproc.process | |
marytts.signalproc.sinusoidal.hntm.analysis |
Analysis package for harmonics plus noise speech models.
|
marytts.tools.analysis | |
marytts.util.data.text |
Various relatively generic utilities for text input/output.
|
marytts.util.signal |
Various relatively generic utilities for signal processing.
|
Modifier and Type | Method and Description |
---|---|
LsfMatch |
TargetLsfCopyMapper.transform(double sourceTime,
Labels sourceLabels,
Labels targetLabels,
double[][] targetLsfs,
double targetLsfAnalysisWindowSizeInSeconds,
double targetLsfAnalysisSkipSizeInSeconds) |
Constructor and Description |
---|
Context(Labels labels,
int currentLabelIndex,
int totalNeighbours) |
Context(Labels labels,
int currentLabelIndex,
int totalLeftNeighbours,
int totalRightNeighbours) |
Modifier and Type | Method and Description |
---|---|
void |
BasicProsodyModifierParams.init(PitchReaderWriter f0Src,
Labels labSrc,
PitchReaderWriter f0Tgt,
Labels labTgt,
boolean isPitchScale,
boolean isTimeScale) |
Constructor and Description |
---|
BasicProsodyModifierParams(PitchReaderWriter f0Src,
Labels labSrc,
PitchReaderWriter f0Tgt,
Labels labTgt,
boolean isPitchScale,
boolean isTimeScale) |
Modifier and Type | Field and Description |
---|---|
Labels[] |
FestivalUtt.labels |
Modifier and Type | Method and Description |
---|---|
Labels |
AlignedLabels.getFirst() |
Labels |
AlignedLabels.getSecond() |
Constructor and Description |
---|
AlignedLabels(Labels first,
Labels second,
int[] indexMap) |
Labels(Labels e) |
Modifier and Type | Method and Description |
---|---|
static double[] |
Blizzard09PostProcessor.process(double[] x,
Labels labels,
Allophone[] allophones,
int samplingRateInHz,
double absMaxOrig) |
static double[] |
Blizzard09PostProcessor.processGains(double[] x,
int samplingRateInHz,
Labels labels,
boolean[] toBeProcesseds,
double extremumGainFactor,
double extremumGainRelativeDuration) |
static double[] |
Blizzard09PostProcessor.processHigherFormantGains(double[] x,
int samplingRateInHz,
Labels labels,
boolean[] isPauses) |
static double[] |
Blizzard09PostProcessor.processLSFs(double[] x,
int samplingRateInHz,
Labels labels,
boolean[] isVowels,
boolean[] isPauses) |
Modifier and Type | Method and Description |
---|---|
HntmSpeechSignal |
HntmAnalyzer.analyze(double[] x,
int fs,
PitchMarks pm,
double f0WindowSizeInSeconds,
double f0SkipSizeInSeconds,
float[] f0Contour,
Labels labels,
HntmAnalyzerParams analysisParams,
HntmSynthesizerParams synthesisParamsBeforeNoiseAnalysis,
String analysisResultsFile) |
HntmSpeechSignal |
HntmAnalyzer.analyze(double[] x,
int fs,
PitchReaderWriter f0,
Labels labels,
HntmAnalyzerParams analysisParams,
HntmSynthesizerParams synthesisParamsBeforeNoiseAnalysis,
String analysisResultsFile) |
HntmSpeechSignal |
HntmAnalyzer.analyze(short[] x,
int fs,
PitchMarks pm,
double f0WindowSizeInSeconds,
double f0SkipSizeInSeconds,
float[] f0Contour,
Labels labels,
HntmAnalyzerParams analysisParams,
HntmSynthesizerParams synthesisParamsBeforeNoiseAnalysis,
String analysisResultsFile) |
HntmSpeechSignal |
HntmAnalyzer.analyze(short[] x,
int fs,
PitchReaderWriter f0,
Labels labels,
HntmAnalyzerParams analysisParams,
HntmSynthesizerParams synthesisParamsBeforeNoiseAnalysis) |
HntmSpeechSignal |
HntmAnalyzer.analyze(short[] x,
int fs,
PitchReaderWriter f0,
Labels labels,
HntmAnalyzerParams analysisParams,
HntmSynthesizerParams synthesisParamsBeforeNoiseAnalysis,
String analysisResultsFile) |
HarmonicAndTransientAnalysisOutput |
HntmAnalyzer.analyzeHarmonicAndTransientParts(double[] x,
int fs,
PitchMarks pm,
double f0WindowSizeInSeconds,
double f0SkipSizeInSeconds,
float[] f0Contour,
Labels labels,
HntmAnalyzerParams analysisParams) |
HarmonicAndTransientAnalysisOutput |
HntmAnalyzer.analyzeHarmonicAndTransientParts(double[] x,
int fs,
PitchReaderWriter f0,
Labels labels,
HntmAnalyzerParams analysisParams) |
Modifier and Type | Method and Description |
---|---|
AlignedLabels |
TranscriptionAligner.alignLabels(Labels first,
Labels second)
Align the two given sequences of labels and return a mapping array indicating which index in first should be aligned to
which index in second.
|
void |
CopySynthesis.imposeDurations(Labels source,
Document target)
Make sure that the label sequence as provided in source is copied into the target document, and that the phone and boundary
durations in the target are adjusted to those in source.
|
void |
CopySynthesis.imposeIntonation(Labels durationAndSegmentSource,
PraatPitchTier pitchSource,
Document target)
Make sure that 1.
|
void |
CopySynthesis.imposeSegments(Labels source,
Document target)
Make sure that the label sequence as provided in source is copied into the target document.
|
void |
SynthesizeToPitchTier.synthPredictedPitchTier(String input,
Labels reference,
String filename) |
Modifier and Type | Method and Description |
---|---|
Labels |
XwavesLabelfileReader.getLabels() |
Modifier and Type | Method and Description |
---|---|
static int |
SignalProcUtils.frameIndex2LabelIndex(int zeroBasedFrameIndex,
Labels labels,
double windowSizeInSeconds,
double skipSizeInSeconds) |
static int[] |
SignalProcUtils.mapFrameIndices(int numfrmSource,
Labels srcLabs,
double srcWindowSizeInSeconds,
double srcSkipSizeInSeconds,
int numFrmTarget,
Labels tgtLabs,
double tgtWindowSizeInSeconds,
double tgtSkipSizeInSeconds) |
static double[] |
SignalProcUtils.normalizeVocalTract(double[] srcSignal,
double[] tgtSignal,
Labels sourceLabels,
Labels targetLabels,
int windowType,
double windowSizeInSeconds,
double frameShiftInSeconds,
int lpcOrder,
int samplingRateInHz,
float preCoef) |
static double |
SignalProcUtils.sourceTime2targetTime(double sourceTime,
Labels sourceLabels,
Labels targetLabels) |
static double |
SignalProcUtils.sourceTime2targetTime(double sourceTime,
Labels sourceLabels,
Labels targetLabels,
int[][] map) |
static int |
SignalProcUtils.time2LabelIndex(double time,
Labels labels) |
Copyright © 2000–2016 DFKI GmbH. All rights reserved.