I want to build my own TTS (Text to Speech) App using HTS (HMM-based speech synthesis system) for Indonesian language.
I have a problem when I want to change the Context-dependent-label and question-set to that suitable for my language. How can I do this?
So far, what I know is I have to change context-dependent-label in file
data/script/label-full.awk
and question-set in file
data/script/questions/qst_[verion].hed
(I use HTS training demo for sample project). When I open these files, I get this:
label-full.awk### SEGMENT
# boundary
printf "%10.0f %10.0f ", 1e7 * $65, 1e7 * $66 # pp.name
printf "%s", ($63 == "0") ? "x" : $63 # p.name
printf "^%s", ($1 == "0") ? "x" : $1 # c.name
printf "-%s", $2 # n.name
printf "+%s", ($3 == "0") ? "x" : $3 # nn.name
printf "=%s", ($64 == "0") ? "x" : $64
bla..bla..bla..
and for .hed file:
QS "LL-Vowel" {aa^,ae^,ah^,ao^,aw^,ax^,axr^,ay^,eh^,el^,em^,en^,er^,ey^,ih^,ix^,iy^,ow^,oy^,uh^,uw^*}
QS "LL-Consonant" {b^,ch^,d^,dh^,dx^,f^,g^,hh^,hv^,jh^,k^,l^,m^,n^,nx^,ng^,p^,r^,s^,sh^,t^,th^,v^,w^,y^,z^,zh^*}
QS "LL-Stop" {b^,d^,dx^,g^,k^,p^,t^*}
QS "LL-Nasal" {m^,n^,en^,ng^}
QS "LL-Fricative" {ch^,dh^,f^,hh^,hv^,s^,sh^,th^,v^,z^,zh^*}
QS "LL-Liquid" {el^,hh^,l^,r^,w^,y^}
QS "LL-Front" {ae^,b^,eh^,em^,f^,ih^,ix^,iy^,m^,p^,v^,w^}
QS "LL-Central" {ah^,ao^,axr^,d^,dh^,dx^,el^,en^,er^,l^,n^,r^,s^,t^,th^,z^,zh^*}
QS "LL-Back" {aa^,ax^,ch^,g^,hh^,jh^,k^,ng^,ow^,sh^,uh^,uw^,y^*}
bla..bla..bla...
What's the meaning of that string? How to customize or add a new context (like the tone of one syllable) to these files?