5,710
edits
Changes
→Building a Unit Selection Cluster Voice from TIMIT data
[[Home | <<< back to Wiki Home]]
=Getting Started=
*Festival Speech Synthesis System - http://www.cstr.ed.ac.uk/projects/festival/
*this is useful build on os x with do_prompt capabilities - http://linguisticmystic.com/2011/07/15/using-festival-tts-on-os-x/**http://permalink.gmane.org/gmane.science.tts.festvox/381
*this is a class - http://www.speech.cs.cmu.edu/15-492/assignments/tts/index.html
=Learning=
*Book - http://festvox.org/festvox/book1.html
*short tutorial - http://festvox.org/festtut-2.0/
*exercises and hints - http://festvox.org/festtut-2.0/exercises/
==Slides on HTS Synthesis==*http://www.sp.nitech.ac.jp/~tokuda/tokuda_iscslp2006.pdf =Training a Voice ModelModels=
*howto http://festvox.org/festvox/c3170.html#AEN3172
*training text input - http://www.festvox.org/cmu_arctic/cmuarctic.data
*useful tips http://festvox.org/index.html, including name for EMU speech database system http://www.shlrc.mq.edu.au/emu/
*Building a CLUSTERGEN Statistical Parametric Synthesizer: http://festvox.org/festvox/c3170.html#AEN3172
==Building a Unit Selection Cluster Voice==
(from here http://festvox.org/festvox/x3086.html)
#<pre>mkdir uw_uw_rdt
cd uw_uw_rdt</pre>
#uniphone setup: <pre> $FESTVOXDIR/src/unitsel/setup_clunits uw us rdt uniphone</pre>
#generate prompts and prompt files: <pre>festival -b festvox/build_clunits.scm '(build_prompts_waves "etc/uniphone.data")'</pre>
#record sound, using audacity. save as 16k, 16bit mono.
#make labels: <pre>./bin/make_labs prompt-wav/*.wav</pre>
#build utterance structure: <pre>festival -b festvox/build_clunits.scm '(build_utts "etc/uniphone.data")'</pre>
#do pitch marking: <pre>./bin/make_pm_wave etc/uniphone.data</pre>
#find Mel Frequency Cepstral Coefficients: <pre>./bin/make_mcep etc/uniphone.data</pre>
#build cluster unit selection synth: <pre>festival -b festvox/build_clunits.scm '(build_clunits "etc/uniphone.data")'</pre>
==Using a Unit Selection Cluster Voice Synth==
#from uw_us_rdt directory: <pre>festival festvox/uw_us_rdt_clunits.scm</pre>
#in Scheme:<pre>(voice_uw_us_rdt_clunits) </pre>
#<pre>(SayText "this is a little test.")</pre>
==Building a CLUSTERGEN Statistical Parametric Synthesizer==
(adapted from http://festvox.org/festvox/c3174.html#AEN3176)
#<pre>mkdir uw_us_rdt_arctic</pre>
#<pre>cd uw_us_rdt_arctic</pre>
#<pre>$FESTVOXDIR/src/clustergen/setup_cg uw us rdt_arctic</pre>
#copy text into <pre>etc/txt.done.data</pre>. use some of the lines from here http://www.festvox.org/cmu_arctic/cmuarctic.data
#copy audio files into <pre>wav/</pre>
#use <pre>bin/get_wavs</pre> to copy files to power normalize and convert to proper format.
==Building a Unit Selection Cluster Voice from TIMIT data==
(from here http://festvox.org/festvox/c2645.html#AEN2716)
#<pre>mkdir uw_uw_rdt_timit</pre>
#<pre>cd uw_uw_rdt_timit</pre>
#timit setup: <pre> $FESTVOXDIR/src/unitsel/setup_clunits uw us rdt timit</pre>
#generate prompts and prompt files: <pre>festival -b festvox/build_clunits.scm '(build_prompts_waves "etc/timit.data")'</pre>
#record sound, using audacity. save as 16k, 16bit mono.
#copy sound files from recording directory into voice directory. <pre> ./bin/get_wavs ~/Sounds/TIMIT_Training_Data/warehouse_omni/*.wav </pre>
#make labels: <pre>./bin/make_labs prompt-wav/*.wav</pre>
#build utterance structure: <pre>festival -b festvox/build_clunits.scm '(build_utts "etc/timit.data")'</pre>
#do pitch marking: <pre>./bin/make_pm_wave etc/timit.data</pre>
#find Mel Frequency Cepstral Coefficients: <pre>./bin/make_mcep etc/timit.data</pre>
#build cluster unit selection synth: <pre>festival -b festvox/build_clunits.scm '(build_clunits "etc/timit.data")'</pre>
=Improving Quality=
*Fix phoneme labeling - http://sourceforge.net/projects/wavesurfer/
*tuning a voice - http://www.cstr.ed.ac.uk/emasters/summer_school_2005/tutorial3/tutorial.html
= Using Voices =
== using meghan voice ==
=== Run the Server ===
*open terminal:
<pre>
cd /Users/murmur/Desktop/meghan
festival_server -c meghans_special_sauce.scm
</pre>
*To kill the server:
<pre>Control-C</pre>
=== Run the Client ===
*open a 2nd terminal window:
<pre>
cd /Users/murmur/Desktop/meghan
festival_client myfile.txt --ttw --output client_test.wav
</pre>
*Other stuff (python):
<pre>
import os
os.popen("/Applications/festival_2.1/festival/src/main/festival_client /Users/murmur/Desktop/meghan/myfile.txt --ttw --output /Users/murmur/Desktop/meghan/client_test78.wav")
</pre>
==Using A Newly Trained Voice ==
===Modify the voice so festival knows it's there===
*append proclaim message to your newly trained model <code>uw_us_rdt_clunits.scm</code> in <code>uw_us_rdt_clunits/festvox</code>:
<pre>
(proclaim_voice
'uw_us_rdt_clunits
'((language english)
(gender male)
(dialect american)
(description
"This is Robert Twomey trained on CLUNITS, TIMIT databse.")))
(provide 'uw_us_rdt_clunits)
</pre>
===Install voice to festival directory===
*http://roberttwomey.com/downloads/uw_us_rdt_clunits.tar.gz
*unzip file from festival root directory, it should install to the correct directory
*copy your newly trained voice to <code>festival/lib/voices/english/</code>
*the name of your new voice directory (ex: <code>uw_us_rdt_clunits/</code>) needs to match the voice file (ex: <code>uw_us_rdt_clunits/festvox/uw_us_rdt_clunits.scm</code>)
===Configure festival to use your voice by default===
*to set your voice as default (and add a special pause entry), add the following to <code>festival/etc/siteinit.scm</code>:
<pre>
(set! voice_default 'voice_uw_us_rdt_clunits)
(lex.add.entry '("<break>" n (((pau pau) 0))))
</pre>
*the <code>lex.add.entry</code> line makes a new word in the lexicon <code><break></code> that adds a pause.
*run <code>festival_server</code> and it will load your new voice by default
*http://www.cstr.ed.ac.uk/projects/festival/manual/festival_24.html
=Add a pause as a new lexical entry=
*add the following after <code> (provide 'siteinit) </code> in <code>festival/etc/siteinit.scm</code>:
<pre>
(voice_uw_us_rdt_clunits)
(lex.add.entry '("<break>" n (((pau pau) 0))))
</pre>
*this will add a new word, "<break>" that is synthesized as a brief pause in speech.
=Using Voice on Raspberry Pi=
*install with apt-get. alternatively, follow these instructions: http://elinux.org/RPi_Text_to_Speech_(Speech_Synthesis)
*With festival 2.1
*copy the voice data into <code>/usr/share/festival/voices/english</code>
*edit '''/usr/share/festival/voices.scm''' and add the new voice <code>uw_us_rdt_clunits</code> at the beginning of the default-voice-priority-list. (end of the file)
*now your new voice should be the default for festival.
==rpi with external i2s dac==
*change aplay command within festival/scheme:
<syntaxhighlight lang="bash">
(Parameter.set 'Audio_Command "aplay -q -c 2 -t raw -f s16 -r 8000 $FILE")"
</syntaxhighlight>
*or add to startup: https://wiki.archlinux.org/index.php/Festival#Usage_with_a_Sound_Server
=Tuning phrasing, prosody, etc with SABLE=
*http://www.cstr.ed.ac.uk/projects/festival/manual/festival_10.html#SEC31
=Using Festival=
==Run the Server==
*from anywhere: <code>festival_server</code>
==Run the Client==
*run the client: <code>echo "Do you really want to see all of it?" | festival_client --ttw --output test.wav </code>
*generates a wave file
==Synthesize Speech to Audio Out==
*run festival: <code>echo "test this" | festival --tts</code>
*plays through speakers.
==Render a Text File In Speech==
*run the server
*run the client: <code>cat ~/Documents/speech\ performance/speech\ performance\ structure.txt | festival_client --ttw --output structure.wav</code>
==Phoneme tests==
Switch voices:
<syntaxhighlight lang="scheme">(voice_kal_diphone)</syntaxhighlight>
Switch back:
<syntaxhighlight lang="scheme">(voice_uw_us_rdt_clunits)</syntaxhighlight>
Pronounce phonemes:
<syntaxhighlight lang="scheme">(SayPhones '(pau ch pau m ay n ey m ih z r ah b er t pau)) </syntaxhighlight>
<syntaxhighlight lang="scheme">(SayPhones '(pau ch pau m ay n ey m ih z r ow b er t pau)) </syntaxhighlight>
<syntaxhighlight lang="scheme">(SayPhones '(pau ch pau m ay n ey m ih z r ow b ah t pau)) </syntaxhighlight>
<syntaxhighlight lang="scheme">(SayPhones '(pau ch pau m ay n ey m ih z r ah b ah t pau)) </syntaxhighlight>
