Changes between Version 2 and Version 3 of HMMVoiceCreation-MARY-5.0

Timestamp:

11/07/11 16:29:04 (14 years ago)

Author:

marcela_charfuelan

Comment:

--

HMMVoiceCreation-MARY-5.0

@@ -4 +4 @@
 For creating HMM-based voices we use a version of the speaker dependent training scripts provided by [http://hts.sp.nitech.ac.jp/ HTS] that was adapted to the MARY 4.1.0 platform. The steps for building a HMM voice for the MARY platform can be summarised in:[[BR]]
 
-I) Download MARY TTS including Voice import tools[[BR]]
-II) Check necessary programs and files[[BR]]
-III) Check data: audio and text files[[BR]]
-IV) Run the Voice import tools [[BR]]
-V) Creating other voice in a language different from German or English (US).
-VI) Adaptive scripts
+I) [#point1 Download MARY TTS including Voice import tools] [[BR]]
+II) [#point2 Check necessary programs and files] [[BR]]
+III) [#point3 Check data: audio and text files] [[BR]]
+IV) [#point4 Run the Voice import tools] [[BR]]
+V) [#point5 Creating other voice in a language different from German or English (US).] [[BR]]
+VI) [#point6 Adaptive scripts] [[BR]]
+
 
 The training scripts used here are the latest versions, that is, it is required HTS_2.2 and HTK-3.4.1. Some scripts have been added-modified to:[[BR]]
@@ -21 +22 @@
 
 '''
-== I) Download MARY TTS including Voice import tools ==
+== I) [=#point1] Download MARY TTS including Voice import tools ==
 '''
 
@@ -37 +38 @@
 
 '''
-== II) Check the necessary programs and files: ==
+== II) [=#point2]Check the necessary programs and files: ==
 '''
 
@@ -78 +79 @@
 
 '''
-== III) Check data: audio and text files[[BR]] ==
+== III) [=#point3] Check data: audio and text files[[BR]] ==
 '''
 
@@ -88 +89 @@
 
 '''
-== IV) Run the Voice Import tools ==
+== IV) [=#point4] Run the Voice Import tools ==
 '''
 
@@ -234 +235 @@
 cp /voicebuildingdir/mary/voice-yourvoice-hsmm/target/voice-yourvoice-hsmm-5.0-SNAPSHOT.jar $MARY_BASE/target/marytts-5.0-SNAPSHOT/lib/
 }}}
-'''
-=== V) Creating other voice in a language different from German or English (US). ===
-'''
+
+== '''V) [=#point5] Creating other voice in a language different from German or English (US)''' ==
+ 
 
 If you are creating a voice in other language you will need to specify:  (NOTE: THIS NEED TO BE UPDATED)
@@ -254 +255 @@
 
 
-=== VI) Adaptive scripts ===
-'''
-
-'''1.''' For running the HTS Speaker adaptation/adaptive training demo we need the following directories in your voicebuilding directory:
-text:
- bdl clb slt jmk rms
-wav:
-  bdl clb slt jmk rms
-
-'''2.''' With the voicebuilding tools we need to create phonelabels and phonefeatures directories for each set of data. This can be done working each set with voicebuilding tools, that is, use the general settings to define where your wave, text, etc. directories are. Then for each data set run the steps 1-8 of the speaker dependent tutorial. As a result we should have the following directories:
-phonelabels
- bdl clb slt jmk rms
-phonefeatures
- bdl clb slt jmk rms
-
-'''3.''' Create raw data from you wav files, this can be done using the script $MARY_BASE/lib/external/hts/data/scripts/wav2raw. As a results we should have the following directories:
-hts/data/raw:
- bdl clb slt jmk rms
-
-'''4.''' Having the previous directories, the run the voiceimportools and excute the steps:
-- HMMVoiceDataPreparation, setting the adaptScripts variable in true
-- HMMVoiceConfigure, setting the adaptScripts variable in true
+
+
+== '''VI) [=#point6] Adaptive scripts''' ==
+
+
+
+
+'''1.''' For running the HTS Speaker adaptation/adaptive training demo we need the following directories in your voicebuilding directory:[[BR]]
+text:[[BR]]
+ bdl clb slt jmk rms[[BR]]
+wav:[[BR]]
+  bdl clb slt jmk rms[[BR]]
+
+
+'''2.''' With the voicebuilding tools we need to create phonelabels and phonefeatures directories for each set of data. This can be done working each set with voicebuilding tools, that is, use the general settings to define where your wave, text, etc. directories are. Then for each data set run the steps 1-8 of the speaker dependent tutorial. As a result we should have the following directories:[[BR]]
+phonelabels:[[BR]]
+ bdl clb slt jmk rms[[BR]]
+phonefeatures:[[BR]]
+ bdl clb slt jmk rms[[BR]]
+
+'''3.''' Create raw data from you wav files, this can be done using the script $MARY_BASE/lib/external/hts/data/scripts/wav2raw. As a results we should have the following directories:[[BR]]
+hts/data/raw:[[BR]]
+ bdl clb slt jmk rms[[BR]]
+
+'''4.''' Having the previous directories, the run the voiceimportools and excute the steps:[[BR]]
+'''4.1''' HMMVoiceDataPreparation, setting the adaptScripts variable in true[[BR]]
+'''4.2''' HMMVoiceConfigure, setting the adaptScripts variable in true[[BR]]
 
 If adapting other sets, be aware of the file names format for the adaptive scripts. Since it is used a mask for the names it is better if the names of your files have a particular format. 
@@ -286 +292 @@
 }}}
 
-Having this distribution of files, our settings for configureAdapt looked like:
+Having this distribution of files, our settings for configureAdapt looked like:[[BR]]
 {{{
 HMMVoiceConfigure.dataSet        = pavoque
@@ -296 +302 @@
 }}}
 
-- HMMVoiceFeatureSelection
-- HMMVoiceMakeData,  setting the adaptScripts variable in true
-- HMMVoiceMakeVoice
-- HMMVoiceCompiler
+'''4.3''' HMMVoiceFeatureSelection[[BR]]
+'''4.4''' HMMVoiceMakeData,  setting the adaptScripts variable in true[[BR]]
+'''4.5''' HMMVoiceMakeVoice[[BR]]
+'''4.6''' HMMVoiceCompiler[[BR]]