Revision as of 07:13, 6 November 2012

<<< back to Wiki Home

Getting Started

• Festival Speech Synthesis System - http://www.cstr.ed.ac.uk/projects/festival/
• 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/

Training Voice Models

• 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/x3082.html)

1. mkdir uw_uw_rdt

1. uniphone setup:

    $FESTVOXDIR/src/unitsel/setup_clunits uw us rdt uniphone

2. generate prompts and prompt files:

   festival -b festvox/build_clunits.scm '(build_prompts_waves "etc/uniphone.data")'

3. record sound, using audacity. save as 16k, 16bit mono.
4. make labels:

   ./bin/make_labs prompt-wav/*.wav

5. build utterance structure:

   festival -b festvox/build_clunits.scm '(build_utts "etc/uniphone.data")'

6. do pitch marking:

   ./bin/make_pm_wave etc/uniphone.data

7. find Mel Frequency Cepstral Coefficients:

   ./bin/make_mcep etc/uniphone.data

8. build cluster unit selection synth:

   festival -b festvox/build_clunits.scm '(build_clunits "etc/uniphone.data")'

Using a Unit Selection Cluster Voice Synth

1. from uw_us_rdt directory:

   festival festvox/uw_us_rdt_clunits.scm

2. in Scheme:

   (voice_uw_us_rdt_clunits) 

3. (SayText "this is a little test.")

Building a CLUSTERGEN Statistical Parametric Synthesizer

adapted from http://festvox.org/festvox/c3170.html#AEN3172

1. mkdir uw_us_rdt_arctic

uw_us_rdt_arctic $FESTVOXDIR/src/clustergen/setup_cg uw us rdt_arctic

1. copy text into etc/txt.done.data. use some of the lines from here http://www.festvox.org/cmu_arctic/cmuarctic.data
2. copy audio files into wav/
3. use

   bin/get_wavs

   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/x3082.html)

1. mkdir uw_uw_rdt_timit

1. timit setup:

    $FESTVOXDIR/src/unitsel/setup_clunits uw us rdt timit

2. generate prompts and prompt files:

   festival -b festvox/build_clunits.scm '(build_prompts_waves "etc/timit.data")'

3. record sound, using audacity. save as 16k, 16bit mono.
4. make labels:

   ./bin/make_labs prompt-wav/*.wav

5. build utterance structure:

   festival -b festvox/build_clunits.scm '(build_utts "etc/timit.data")'

6. do pitch marking:

   ./bin/make_pm_wave etc/timit.data

7. find Mel Frequency Cepstral Coefficients:

   ./bin/make_mcep etc/timit.data

8. build cluster unit selection synth:

   festival -b festvox/build_clunits.scm '(build_clunits "etc/timit.data")'

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

To run the server:

• open terminal:

cd /Users/murmur/Desktop/meghan festival_server -c meghans_special_sauce.scm

• To kill the server:

Control-C

• To run the client:

open a 2nd terminal window: cd /Users/murmur/Desktop/meghan festival_client myfile.txt --ttw --output client_test.wav

• Other stuff (python):

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")

Using new Voices

Modify new voice so festival knows it's there

• append to uw_us_rdt_clunits.scm in uw_us_rdt_clunits/festvox:

'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)

=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 festival/lib/voices/english/
• the name of your new voice directory (ex: uw_us_rdt_clunits/) needs to match the voice file (ex: uw_us_rdt_clunits/festvox/uw_us_rdt_clunits.scm)

Configure festival to use your voice by default

• to set your voice as default, add the following to festival/etc/siteinit.scm:

(autoload voice_uw_us_rdt_clunits "/Users/rtwomey/code/tts/festival/lib/voices/english/uw_us_rdt_clunits/festvox/uw_us_rdt_clunits" "American English male uw_us_rdt_clunits")

(set! voice_default 'voice_uw_us_rdt_clunits)

(voice_uw_us_rdt_clunits)
(lex.add.entry '("<break>" n (((pau pau) 0))))

• the lex.add.entry line makes a new word in the lexicon

  <break>

  that adds a pause.
• change directory cd to the folder containing your festvox files (trained model)
• run festival_server and it will load your new voice by default
• http://www.cstr.ed.ac.uk/projects/festival/manual/festival_24.html

Tuning phrasing, prosody, etc with SABLE

• http://www.cstr.ed.ac.uk/projects/festival/manual/festival_10.html#SEC31