Changes between Version 10 and Version 11 of VoiceImportToolsTutorial


Ignore:
Timestamp:
09/17/07 07:39:18 (17 years ago)
Author:
sach01
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • VoiceImportToolsTutorial

    v10 v11  
    163163 
    164164'''!PraatPitchmarker'''[[BR]] 
     165 
    165166It computes pitch markers with help of Praat. You need to compile or install Praat in your machine.[[BR]] 
    166167 
     
    190191 
    191192'''Festvox2MaryTranscripts''' [[BR]] 
     193 
    192194This Component supports user to convert Festvox Transcription format (ex: txt.done.data) to MARY Supportable format. MARY contains individual text files for each wave file.  
    193195All Voice Import Components use Transcription from MARY Format. So This component is very useful, if user have Transcription in Festvox format. 
     
    199201    
    200202'''Mary2FestvoxTranscripts'''[[BR]] 
     203 
    201204It supports user to convert MARY Supportable format to Festvox format Transcription. It does reciprocal process to above component. 
    202205 
     
    209212 
    210213'''!PhoneUnitFeatureComputer'''[[BR]] 
     214 
    211215!PhoneUnitFeatureComputer computes Phone feature vectors for Unit Selection Voice building process. [[BR]] 
    212216 * Note: This module requires a running Maryserver from MARY Installation. [[BR]] 
     
    223227 
    224228'''!HalfPhoneUnitFeatureComputer''' 
     229 
    225230This component also same as above component. But It computes Half phone level feature vectors. Here "halfphone-targetfeatures.config" file, which is in Marybase/conf/ directory directs Server to compute Half-Phone level feature vectors. 
    226231 
     
    236241 
    237242'''EHMMLabeler'''[[BR]] 
     243 
    238244EHMM Labeler is a labeling tool, which generates label files with help of Wave files and corresponding Transcriptions. EHMM basic tool is available with Festvox Recent Version.  For running EHMM Labeler under MARY environment you need to compile EHMM tool in your machine. It may take long time depending on the size of the data and system configuration. 
    239245 
     
    262268 
    263269'''!SphinxLabelingPreparator'''[[BR]] 
     270 
    264271This Component prepares the required setup needed for !SphinxTrain to train Models. [[BR]] 
    265272 
     
    274281 
    275282'''!SphinxTrainer'''[[BR]] 
     283 
    276284It trains models required for labeling using Sphinxtrain. It may take long time depending on the size of the data and system configuration. 
    277285 
     
    293301 
    294302'''MRPALabelConverter'''[[BR]] 
     303 
    295304If you have labeled data in the Festvox format and using the MRPA-Phoneset, use this module to convert the phones into the phoneset used by Mary. 
    296305 
     
    308317 * corrPmDir - Directory Path for corrected pitch marks.  
    309318 
    310  
    311  
    312  
     319'''!PhoneUnitLabelComputer'''  and  '''!HalfPhoneUnitLabelComputer'''[[BR]] 
     320 
     321These components converts the label files into the label files used by Mary. !PhoneUnitLabelComputer produces phone labels, !HalfPhoneUnitLabelComputer produces halfphone labels. User need both to build the voice. 
     322 
     323Configuration Settings: 
     324 
     325 * labelDir - Output phone label dir. path for !PhoneUnitLabelComputer.  
     326              Output Half phone label dir. path !HalfPhoneUnitLabelComputer.   
     327 
     328'''!PhoneLabelFeatureAligner'''[[BR]] 
     329 
     330It tries to align the labels and the feature vectors. If alignment fails, you can start the automatic pause correction.[[BR]] 
     331 
     332This works as follows: 
     333 
     334 - pauses, that are in the label file but not in the feature file are deleted in the label file, and the durations of the previous and next labels are stretched. 
     335 - pauses that are in the feature file but not in the label file are inserted into the label file with length zero. 
     336 
     337 
     338If there are still errors after the pause correction, you are prompted for each error. You can skip the error or remove the corresponding file from the basename list (the list of files that are used for your voice). "skip all" and "remove all" does this for all problematic files. "Edit unit labels" allows you to edit the label file. "Edit RAWMARYXML" lets you edit the maryxml that is the input for computing the features. You have to have a Maryserver running in order to recompute the features from the maryxml. You can alter the host and port settings for the server by altering the settings for the !UnitFeatureComputer.  
     339 
     340Configaration Settings: 
     341 
     342 * featureDir - Phone feature vectors directory  
     343 * labDir     - Phone Labels directory 
     344 
     345'''!HalfPhoneLabelFeatureAligner'''[[BR]] 
     346 
     347It also works same as !PhoneLabelFeatureAligner, but it works for halfphone units case.  
     348 
     349Configaration Settings: 
     350 
     351 * featureDir - Half Phone feature vectors directory  
     352 * labDir     - Half Phone Labels directory 
     353 
     354 
     355   
    313356 
    314357( '''Under Construction''' - to continued)