Changes between Version 8 and Version 9 of HMMVoiceCreationMary4.0


Ignore:
Timestamp:
09/24/09 14:54:26 (16 years ago)
Author:
marcela_charfuelan
Comment:

--

Legend:

Unmodified
Added
Removed
Modified

  • HMMVoiceCreationMary4.0

    v8 v9  
    2424'''MARY requirements:'''[[BR]] 
    2525- Operating System - Linux (tested on Ubuntu 9.04) [[BR]] 
    26 - MARY TTS Recent Version - Download link: http://mary.dfki.de/Download [[BR]] 
    27 - Openmary - SVN from:[[BR]] 
    28 {{{ 
    29    svn checkout https://mary.opendfki.de/repos/trunk openmary 
    30 }}} 
     26- MARY TTS 4.0 (beta) including Voice import tools during installation - link: http://mary.dfki.de/download/4.0%20beta/openmary-standalone-install-4.0beta.jar [[BR]] 
    3127- HTS '''speaker dependent training demo''' adapted to the MARY 4.0 beta platform: 
    32      * without SLT data (112K):  included in the openmary directory: openmary/lib/hts/HTS-demo_for_MARY-4.0-beta.tar.gz [[BR]] 
    33      * with SLT data (92MB): link: https://mary.opendfki.de/HTS-demo_CMU-ARCTIC-SLT_for_MARY-4.0-beta.tar.gz [[BR]] 
     28     * without CMU-ARCTIC-SLT data (112K):  included in your MARY TTS 4.0 beta installation: $MARY_BASE/lib/hts/HTS-demo_for_MARY-4.0-beta.tar.gz [[BR]] 
     29     * with CMU-ARCTIC-SLT data (92MB) - link: http://mary.dfki.de/download/4.0%20beta/HTS-demo_CMU-ARCTIC-SLT_for_MARY-4.0-beta.tar.gz [[BR]] 
    3430 
    3531'''HTS requirements:''' please download and follow the instructions for installing:[[BR]] 
    … …  
    4541- perl normally available in linux [[BR]] 
    4642- bc normally available in linux [[BR]] 
    47 - sox, Minimum SoX v13.0.0, normally available in linux. link: http://sox.sourceforge.net/ [[BR]] 
     43- sox, minimum SoX v13.0.0, normally available in linux. link: http://sox.sourceforge.net/ [[BR]] 
    4844- tcl supporting snack, for example  ActiveTcl. link: http://www.activestate.com/Products/ActiveTcl/ [[BR]] 
    4945- snack library for tcl. link: http://www.speech.kth.se/snack/download.html  [[BR]] 
    … …  
    5854''' 
    5955 
    60 Where to start? There are three options: 
     56Where to start? There are three options a, b and c: 
    6157 
    6258'''a-''' If you would like to try the HTS-demo_CMU-ARCTIC-SLT for MARY 4.0 beta from scratch:[[BR]] 
    … …  
    6864 
    6965'''b-''' If you have already created a unit selection voice for MARY, with the CMU-ARCTIC-SLT data, and want to build a HMM-based voice for that,  
    70 copy the openmary/lib/hts/HTS-demo_for_MARY-4.0-beta.tar.gz (112K) in your unit selection voice creation directory and unpack the file: 
     66copy the $MARY_BASE/lib/hts/HTS-demo_for_MARY-4.0-beta.tar.gz (112K) in your unit selection voice creation directory and unpack the file: 
    7167{{{ 
    7268   tar -zxvf HTS-demo_for_MARY-4.0-beta.tar.gz 
    … …  
    7571 
    7672'''c-''' If you want to create a HMM voice in other language please see the section V or VI below.[[BR]] 
     73 
    7774 
    7875Once you have unpacked the HTS demo for MARY 4.0 beta, follow the steps: 
    … …  
    8582If all the necessary programs are installed correctly you can continue with step 2.  
    8683 
    87 '''2-''' Run the VoiceImport program 
    88  
    89 If you have installed MARY 4.0 beta and the voicebuilding component, you can start the VoiceImport program from '''Applications -> OpenMary -> Voice import tools'''[[BR]] 
    90 Otherwise you can run it on a terminal in your working directory (the directory where you have unpacked the HTS demo for MARY 4.0 beta), first you need to set your MARY_BASE directory and then run the voiceimport.jar program: 
    91 {{{ 
    92    export MARY_BASE="/dir/to/openmary" 
    93    java -jar -Xmx1024m  $MARY_BASE/java/voiceimport.jar 
    94 }}} 
    95  
    96 When starting the voiceimport tools, go to your working directory (the directory where you have unpacked the HTS demo for MARY 4.0 beta) and provide information for: 
     84'''2-''' Run the Voice Import Tools program 
     85 
     86The Voice Import Tools programs can be started from: '''Applications -> OpenMary -> Voice import tools'''[[BR]] 
     87 
     88When starting the voice import tools, go to your working directory (the directory where you have unpacked the HTS demo for MARY 4.0 beta) and provide information for: 
    9789{{{ 
    9890  db.gender    = female 
    9991  db.locale    = en_US 
    100   db.marybase  = /path-to-MARY_BASE/ or /path-to-openmary/ 
     92  db.marybase  = /path/to/$MARY_BASE/ 
    10193  db.voicename = slt-hsmm 
    10294}}} 
    103 If you are not familiar or have problems with the VoiceImport program, please read the instructions in the Voice Import Tools 
    104 Tutorial: http://mary.opendfki.de/wiki/VoiceImportToolsTutorial 
     95If you are not familiar or have problems with the Voice Import Tools program, please read the instructions in the Tutorial: http://mary.opendfki.de/wiki/VoiceImportToolsTutorial 
    10596 
    10697Please remember that whenever you are in doubt about the settings of a particular component you can check its corresponding help for a description of the meaning 
    10798(and possible values) of each variable. 
    10899 
    109 After starting the voiceimport tools check the global settings of the voice, make sure that the allophones file is provided and exist: 
    110 {{{ 
    111 db.alophonesSet = MARY_PATH/lib/modules/xx/lexicon/allophones.xx.xml  (where xx is the corresponding language) 
     100After starting the Voice Import Tools check the global settings of the voice, make sure that the allophones file is provided and exist: 
     101{{{ 
     102db.alophonesSet = $MARY_BASE/lib/modules/xx/lexicon/allophones.xx.xml  (where xx is the corresponding language) 
    112103}}} 
    113104 
    … …  
    190181}}} 
    191182 
    192 The allophones set file is language dependent, it can be found in MARY_PATH/lib/modules/en/us/lexicon/allophones.en_US.xml[[BR]] 
     183The allophones set file is language dependent, it can be found in $MARY_BASE/lib/modules/en/us/lexicon/allophones.en_US.xml[[BR]] 
    193184The hmmFeatures.txt is the file created in step 15 and contains additional context features, apart from phone and phonological features, used for training HMMs.[[BR]] 
    194185 
    … …  
    197188  make mgc lf0 str mag cmp-mary gv-mary gv list scp  
    198189}}} 
    199 The '''label''' directory and the '''mlf''' files in MARY are done with the voiceimport tools: HMMVoiceMakeData.makeLabels()[[BR]] 
    200 The '''questions''' file in MARY is done with the voiceimport tools: HMMVoiceMakeData.makeQuestions()  
     190The '''label''' directory and the '''mlf''' files in MARY are done with the Voice Import Tools: HMMVoiceMakeData.makeLabels()[[BR]] 
     191The '''questions''' file in MARY is done with the Voice Import Tools: HMMVoiceMakeData.makeQuestions()  
    201192 
    202193 
    … …  
    256247  * a wav or raw directory with the speech files you will use for training the German voice. [[BR]] 
    257248  * transcriptions of the files, one text file per speech file, or transcriptions in festival format if available. [[BR]] 
    258 then copy the openmary/lib/hts/HTS-demo_for_MARY-4.0-beta.tar.gz file in the directory where you have your wav and transcription data and unpack the file: 
     249then copy the $MARY_BASE/lib/hts/HTS-demo_for_MARY-4.0-beta.tar.gz file in the directory where you have your wav and transcription data and unpack the file: 
    259250{{{ 
    260251   tar -zxvf HTS-demo_for_MARY-4.0-beta.tar.gz 
    … …  
    270261 
    271262 
    272 - If you have already created a German unit selection voice for MARY and want to build a HMM-based voice for that, copy the openmary/lib/hts/HTS-demo_for_MARY-4.0-beta.tar.gz (112K) in your unit selection voice creation directory and unpack the file: 
     263- If you have already created a German unit selection voice for MARY and want to build a HMM-based voice for that, copy the $MARY_BASE/lib/hts/HTS-demo_for_MARY-4.0-beta.tar.gz (112K) in your unit selection voice creation directory and unpack the file: 
    273264{{{ 
    274265   tar -zxvf HTS-demo_for_MARY-4.0-beta.tar.gz 
    … …  
    286277- '''Minimal NLP components''': if you are creating a new voice from scratch, for example following the steps in [http://mary.opendfki.de/wiki/NewLanguageSupport], you will need to create Minimal NLP components for the new language. These minimal components are necessary to run the MARY server in the new language and extract context features ('''phonefeatures''' directory). 
    287278 
    288 - '''Phoneme set''':  contained in MARY_BASE/lib/modules/xx/lexicon/allophones.xx.xml , where xx corresponds to the new language. 
     279- '''Phoneme set''':  contained in $MARY_BASE/lib/modules/xx/lexicon/allophones.xx.xml , where xx corresponds to the new language. 
    289280 
    290281- After creating the minimal components, you will need wav files (in a wav directory) and the corresponding transcriptions (one file per wav file in a text directory). [[BR]] 
    291 Then copy the openmary/lib/hts/HTS-demo_for_MARY-4.0-beta.tar.gz file in the directory where you have your wav and transcription data and unpack the file: 
     282Then copy the $MARY_BASE/lib/hts/HTS-demo_for_MARY-4.0-beta.tar.gz file in the directory where you have your wav and transcription data and unpack the file: 
    292283{{{ 
    293284   tar -zxvf HTS-demo_for_MARY-4.0-beta.tar.gz  
    … …  
    309300 
    310301Marcela Charfuelan[[BR]] 
    311 Thu Sep 10 18:14:12 CEST 2009 
     302Thu Sep 24 14:55:06 CEST 2009