Revision as of 10:42, 9 October 2012 (view source) Rtwomey (talk | contribs) (→‎changes) ← Older edit		Revision as of 11:10, 9 October 2012 (view source) Rtwomey (talk | contribs) Newer edit →
Line 16:		Line 16:
	*training text input - http://www.festvox.org/cmu_arctic/cmuarctic.data		*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/		*useful tips http://festvox.org/index.html, including name for EMU speech database system http://www.shlrc.mq.edu.au/emu/
−	*Building a Unit Selection Cluster Voice - http://festvox.org/festvox/x3082.html
	*Building a CLUSTERGEN Statistical Parametric Synthesizer: http://festvox.org/festvox/c3170.html#AEN3172		*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)
		+	#<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 wav/*.wav</pre>
		+	#find Mel Frequency Cepstral Coefficients: <pre>./bin/make_mcep wav/*.wav
		+	</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>
	=changes=		=changes=

---

Revision as of 11:10, 9 October 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 a Voice Model

• 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)

mkdir uw_uw_rdt cd uw_uw_rdt

1. uniphone setup:

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

1. generate prompts and prompt files

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

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

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

#build utterance structure: <pre>festival -b festvox/build_clunits.scm '(build_utts "etc/uniphone.data")'

1. do pitch marking:

   ./bin/make_pm_wave wav/*.wav

2. find Mel Frequency Cepstral Coefficients:

   ./bin/make_mcep wav/*.wav

1. build cluster unit selection synth:

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

Using a Unit Selection Cluster Voice Synth

• from uw_us_rdt directory:

  festival festvox/uw_us_rdt_clunits.scm

• in Scheme:

  (voice_uw_us_rdt_clunits) 

• (SayText "this is a little test.")

changes

• instead of:

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

do:

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

• instead of:

  ./bin/make_pm_wave wav/*.wav

do

./bin/make_pm_wave etc/uniphone.data