I have used HTK toos to get trained HMMs. I have executed till decoding (like HVite for ergodic and bigram). I want know how these HMMs will be used for HTS speech synthesis. Especially what inputs from HTK trained system will be feed into these HTS commands.
You can lookup the demo that is available in the HTS website. It has Perl script called Training.pl and some other complementary files that perform the whole training/synthesizing procedure.
http://hts.sp.nitech.ac.jp/?Download
Lookup the desired commands
https://github.com/MattShannon/HTS-demo_CMU-ARCTIC-SLT-STRAIGHT-AR-decision-tree/blob/master/scripts/Training.pl
PS: I suspect that the HTK that you use to train the models should be the one that is patched by HTS to take care of things like duration modeling, etc.
Hello
I am facing difficulties using HMGenS tool
I have patched the HTK and I can see all the tools compiled , but when I try to use HMGenS too I get : Command not found message