Interface | Description |
---|---|
MaryModule |
A generic interface for Mary Modules.
|
Class | Description |
---|---|
AcousticModeller |
Predict duration and F0 using CARTs or other models
|
APMLParser |
Transforms a APML document into a raw (untokenised) MaryXML document
|
CARTDurationModeller | Deprecated |
CARTF0Modeller | Deprecated |
DummyAllophones2AcoustParams | Deprecated |
DummyDuration2AcoustParams | |
DummyTokens2Words |
Dummy modules to support new language (for phone durations and phone f0)
|
EmotionmlParser |
Transforms a SABLE document into a raw (untokenised) MaryXML document
|
ExternalModule |
A base class for all external Mary modules.
|
ExternalModuleRequest | |
FestivalCaller |
A link to the synthesis part of festival.
|
FestivalCaller.SimpleFestivalClient | |
HalfPhoneTargetFeatureLister | |
HMMDurationF0Modeller | Deprecated |
HTSEngine |
HTSEngine: a compact HMM-based speech synthesis engine.
|
InternalModule |
A stub implementation of the MaryModule interface as a basis for internal modules.
|
JPhonemiser |
The phonemiser module -- java implementation.
|
JTokeniser | |
KlattDurationModeller |
The calculation of acoustic parameters module.
|
KlattDurationModeller.KlattDurationParams | |
MaryXMLToText |
Create simple text from a rawmaryxml document.
|
MinimalisticPosTagger |
Minimalistic part-of-speech tagger, using only function word tags as marked in the Transcription GUI.
|
ModuleRegistry |
A hierarchical repository for Mary modules, allowing the flexible indexing by an ordered hierarchy of datatype, locale and
voice.
|
OpenNLPPosTagger |
Part-of-speech tagger using OpenNLP.
|
PolynomialF0Modeller |
Predict f0 contours using polynomial curves predicted from a directed graph per syllable.
|
PraatTextGridGenerator |
Transforms a full MaryXML document into a Praat TextGrid containing various interesting information; in particular, the source
units and basenames used in unit selection synthesis
|
ProcessTimeoutDestroyer |
Destroy a given process if timeout occurs.
|
PronunciationModel |
This module serves as a post-lexical pronunciation model.
|
ProsodyGeneric |
The generic prosody module.
|
ProsodyGenericFST | |
RealisedAcoustparamsExtractor |
Transforms a full MaryXML document into an MBROLA format string
|
RealisedDurationsExtractor |
Transforms a full MaryXML document into an MBROLA format string
|
SableParser |
Transforms a SABLE document into a raw (untokenised) MaryXML document
|
SimplePhoneme2AP |
Read a simple phone string and generate default acoustic parameters.
|
SoPDurationModeller | |
SoPF0Modeller | |
SSMLParser |
Transforms a SABLE document into a raw (untokenised) MaryXML document
|
Synthesis |
The synthesis module.
|
SynthesisCallerBase |
A base class for a synthesis caller.
|
TargetFeatureLister |
Read a simple phone string and generate default acoustic parameters.
|
TextToMaryXML |
Embed plain text input into a raw (untokenised) MaryXML document.
|
Copyright © 2000–2016 DFKI GmbH. All rights reserved.