Changes between Version 14 and Version 15 of VoiceImportToolsTutorial


Ignore:
Timestamp:
09/18/07 21:17:29 (17 years ago)
Author:
sach01
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • VoiceImportToolsTutorial

    v14 v15  
    66This Tutorial explains the procedure to build a new voice with Voice Import Tools (VIT) under MARY Environment. 
    77 
    8  Voice Import Tool is a Graphical User Interface(GUI), which contains a set of Voice Import Components and helps the user to build new voices under MARY(Modular Architecture for Research in speech sYnthesis) Environment. This GUI Tool designing is primarily aims to build new voices very easily by any user with out knowing much technical details of Speech Synthesis. 
     8Voice Import Tool is a Graphical User Interface(GUI), which contains a set of Voice Import Components and helps the user to build new voices under MARY(Modular Architecture for Research in speech sYnthesis) Environment. This GUI Tool designing is primarily aims to build new voices very easily by any user with out knowing much technical details of Speech Synthesis. 
    99 
    1010Currently, Voice Import Tool supports following  categories mainly: 
     
    6262 - !SphinxLabeler 
    6363 - MRPALabelConverter 
     64 - !LabelledFilesInspector 
     65 - !PhoneUnitLabelComputer  
     66 - !PhoneLabelFeatureAligner  
     67 - !HalfPhoneUnitLabelComputer  
     68 - !HalfPhoneLabelFeatureAligner  
    6469 - !HalfPhoneUnitfileWriter 
    6570 - !HalfPhoneFeatureFileWriter 
     
    438443 
    439444 
    440 For more information, see the example file: Marybase/lib/modules/import/examples/PhoneUnitFeatureDefinition.txt 
     445For more information, see the example file: ''Marybase/lib/modules/import/examples/PhoneUnitFeatureDefinition.txt'' 
    441446 
    442447Configuration Settings: 
     
    480485 
    481486 
    482 ( '''Under Construction''' - to continued) 
    483  
    484  
    485  
    486  
    487  
    488  
     487 
     488 
     489== 8. Unit Selection == 
     490 
     491 
     492'''!HalfPhoneUnitfileWriter'''[[BR]] 
     493 
     494It produces a file containing all halfphone sized units. 
     495 
     496 
     497Configuration Settings: 
     498 
     499 * corrPmDir - directory containing the corrected pitchmarks 
     500 * labelDir - directory containing the halfphone labels 
     501 * unitFile - file containing all halfphone units. Will be created by this module 
     502 
     503 
     504'''!HalfPhoneFeatureFileWriter'''[[BR]] 
     505 
     506It produces a file containing all the target cost features for the phone sized units. The module needs a file defining which features are to be used and what weights are given to them. They must be the same features as the ones that the !HalfPhoneFeatureComputer used. If you do not have a feature definition, the module tries to create one. 
     507 
     508For more information, see the example file: ''Marybase/lib/modules/import/examples/HalfPhoneUnitFeatureDefinition.txt'' 
     509 
     510Configuration Settings: 
     511 
     512 * featureDir - directory containing the halfphone features 
     513 * featureFile - file containing all halfphone units and their target cost features.Will be created by this module 
     514 * unitFile - file containing all halfphone units 
     515 * weightsFile - file containing the list of halfphone target cost features, their values and weights 
     516 
     517 
     518'''!JoinCostFileMaker'''[[BR]] 
     519 
     520It produces a file containing all the join cost features for the halfphone sized units. 
     521 
     522Configuration Settings: 
     523 
     524 * joinCostFile - file containing all halfphone units and their join cost features. Will be created by this module 
     525 * mcepDir - directory containing the mcep files 
     526 * mcepTimeline - file containing all mcep files 
     527 * unitFile - file containing all halfphone units 
     528 * weightsFile - file containing the list of join cost weights and their weights 
     529 
     530 
     531'''!AcousticFeatureFileWriter'''[[BR]] 
     532 
     533It produces a file containing all the target cost features plus two acoustic target cost features for the halfphone sized units. Also produces a feature definition containing those features. 
     534 
     535 * acFeatDef - file containing the list of phone target cost features, their values and weights 
     536 * acFeatureFile - file containing all halfphone units and their target cost features plus the acoustic target cost features. Will be created by this module. 
     537 * featureFile - file containing all halfphone units and their target cost features 
     538 * unitFile - file containing all halfphone units 
     539 * waveTimeLine - file containing all wave files 
     540 
     541 
     542'''CARTBuilder'''[[BR]] 
     543 
     544It builds a preselection tree for the target cost features using "wagon" (CART) from the Edinburgh Speech tools. 
     545 
     546Additionally, User need to specify either a feature sequence or a top level tree. They are used to built a basic tree that is extendend by wagon. This way, wagon runs several times on smaller subsets of units rather than the whole set. It might still take some time to run this module.  
     547 
     548 - Feature sequence: A file containing a list of features for which to build the tree. 
     549 - Top level tree: A file containing the basic tree. 
     550 
     551For more information on these two possibilities of specifying the basic tree, see the example files in ''Marybase/lib/modules/import/examples/'' 
     552 
     553If you give the CARTBuilder neither a feature sequence nor a top level tree file, a default feature sequence is created which only contains "mary_phoneme" as feature. If the basic tree contains leaves that are contain more units than the maximum number of units allowed, the leaves are pruned and a warning message is printed. It is recommended that you make sure that there are no leaves that are too big. 
     554 
     555 
     556Configuration Settings: 
     557 
     558 * acFeatureFile - file containing all halfphone units and their target cost features plus the acoustic target cost features 
     559 * cartFile - file containing the preselection CART. Will be created by this module 
     560 * estDir - directory containing the local installation of the Edinburgh Speech Tools 
     561 * featureSeqFile - file containing the feature sequence for the basic tree 
     562 * maxLeafSize - the maximum number of units in a leaf of the basic tree 
     563 * mcepTimeline - file containing the mcep files 
     564 * readFeatureSequence - if "true", basic tree is read from feature sequence file; if "false", basic tree is read from top level tree file. 
     565 * topLevelTreeFile - file containing the basic tree 
     566 * unitFile - file containing all halfphone units 
     567 
     568 
     569'''CARTPruner'''[[BR]] 
     570 
     571It prunes the preselection tree and this module also removes outliers from the preselection tree. 
     572 
     573Configuration Settings: 
     574 
     575 * cartFile - file containing the preselection CART 
     576 * prunedCartFile - file containing the pruned preselection CART. Will be created by this module 
     577 * unitFeatureFile - file containing all halfphone units and their target cost features 
     578 * unitFile - file containing all halfphone units 
     579 * waveFile - file containing all wave files 
     580 
     581 
     582 
     583== 9. Installation of New Voice in to MARY == 
     584 
     585 
     586'''!VoiceInstaller'''[[BR]] 
     587 
     588It supports the built voice installation in to MARY automatically. It copies all the necessary files to a new subdirectory in the ''lib/voices/'' directory of your Mary installation. Furthermore, a file that specifies the properties of the voice is created and stored in the ''conf/'' directory of your Mary installation. Next time you start the Mary server, the voice is loaded.  
     589 
     590 
     591Configuration Settings: 
     592 
     593 * cartFile - file containing the preselection CART 
     594 * durTree - file containing the duration CART 
     595 * exampleText - file containing example text (for limited domain voices only) 
     596 * f0LeftTree - file containing the left f0 CART 
     597 * f0MidTree - file containing the mid f0 CART 
     598 * f0RightTree - file containing the right f0 CART 
     599 * halfPhoneFeatDefAc - file containing the list of halfphone target cost features, their values and weights 
     600 * halfPhoneFeatsAc - file containing all halfphone units and their target cost featuresplus the acoustic target cost features 
     601 * halfPhoneUnits - file containing all halfphone units 
     602 * joinCostFeatDef - file containing the list of join cost weights and their weights 
     603 * joinCostFeats - file containing all halfphone units and their join cost features 
     604 * phoneFeatDef - file containing the list of phone target cost features, their values and weights 
     605 * waveTimeline - file containing all wave files  
     606 
     607 
     608 
     609 
     610 
     611 
     612 
     613 
     614 
     615 
     616 
     617